With the rapid advancement of deepfake technologies，including generative adversarial networks （GANs），autoencoders （AEs），and diffusion models （DMs），deepfake facial images have been increasingly exploited for malicious purposes，such as the creation of nonconsensual pornographic content，telecommunication fraud，and the propagation of political disinformation. In recent years，the continuous iteration of these core deepfake technologies has considerably lowered the technical threshold for generating high-fidelity fake facial images： GANs，with their adversarial training mechanism between generators and discriminators，enable the rapid synthesis of realistic facial features； AEs，relying on unsupervised learning and feature reconstruction capabilities，excel in simulating subtle facial expressions and skin textures； diffusion models，through step-by-step noise reduction and feature enhancement，have further broken through the limitations of traditional deepfake technologies in terms of image clarity and detail authenticity，making deepfake facial images increasingly difficult to distinguish with the naked eye and even challenging preliminary manual identification in forensic investigations. As an emerging form of digital evidence，deepfakes not only pervade contemporary criminal activities but also risk being weaponized for false accusations or the tampering of surveillance records，thereby severely undermining the reliability of facial image analysis in forensic science and threatening the integrity of the criminal justice system. To address the aforementioned challenges，this study systematically traces the developmental trajectory of key datasets and the technological evolution of deepfake facial images while conducting an in-depth dissection of the core architecture underlying their generation mechanisms，encompassing primary technical routes，theoretical underpinnings，and functional logics. In terms of dataset development，the evolution process from early small-scale，single-scene datasets （such as CelebA and LFW） to large-scale，multiscenario，high-diversity datasets （such as DFDC，FF++，and Celeb-DF） is sorted out，with the advantages and limitations of each type of dataset analyzed in terms of sample size，fake generation technology coverage，and scene diversity Moreover，the lack of standardized，forensic-oriented datasets has become one of the key bottlenecks restricting the practical application of deepfake detection technologies. In terms of technological evolution，the development of deepfake facial image technology is divided into three stages： the initial exploration stage dominated by GANs，the improvement stage supplemented by AEs，and the mature stage driven by diffusion models. The theoretical breakthroughs and technical improvements of each stage are elaborated，and the internal logic of the continuous improvement of fake image fidelity and the continuous reduction of generation costs is revealed. In the in-depth analysis of generation mechanisms，the core principles of the three mainstream technologies are focused on，the differences in their technical routes and functional characteristics are clarified，and the common key links and potential vulnerabilities in the generation process are summarized，laying a theoretical foundation for the subsequent design of targeted detection and identification methods. On the basis of 737 relevant articles retrieved and screened from the Web of Science database，a bibliometric analysis is performed via VOSviewer to identify research trends in the field and illuminate the substantial disconnect between existing detection technology research and the practical requirements for evidence authentication in judicial practice. The retrieval and screening process strictly followed the PRISMA guidelines： “deepfake”，“facial image”，“forensic science”，“identification”，and “detection” are adopted as key search terms； the retrieval time range is defined from the emergence of deepfake technology to the present； and irrelevant literature，review papers with low innovation，and duplicate publications are excluded through preliminary screening and full-text reading. The bibliometric analysis focuses on three core dimensions： research hotspots，institutional cooperation，and research frontiers. Results show that current research in the field is mainly concentrated on the optimization of detection algorithms （such as deep learning-based feature extraction and classification models），while research on the translation of detection results into forensic authentication，the formulation of forensic identification standards，and the adaptation of detection technologies to judicial practice scenarios is relatively scarce. This disconnect is mainly reflected in two aspects： on the one hand，most existing detection technologies focus on technical accuracy，ignoring the admissibility requirements of judicial evidence （such as objectivity，authenticity，and relevance）； on the other hand，forensic examiners lack effective methods to integrate technical detection results into judicial authentication，leading to the situation where advanced detection technologies fail to be effectively applied in judicial practice. In response to the identified research-practice disconnect，this study proposes a classification of deepfake facial image detection methods into two complementary frameworks： technology principle oriented and application scenario adaptive，designed to address evidence authentication needs across distinct stages. The technology-principle-oriented framework takes the technical principles of deepfake generation as the core，classifies detection methods in accordance with the technical characteristics of different generation technologies （such as GAN-based detection，AE-based detection，and diffusion model-based detection），and focuses on improving the accuracy and generalization ability of detection，thus being mainly applicable to the preliminary technical screening stage of evidence in forensic investigations. The application-scenario-adaptive framework takes the actual needs of different judicial stages （such as investigation，prosecution，and trial） as guidance，classifies detection methods in light of the scenario characteristics and evidence requirements of each stage，and focuses on enhancing the adaptability and operability of detection methods，thereby being mainly applicable to the formal evidence authentication stage in judicial practice. The two frameworks are complementary and mutually supportive： the technology-principle-oriented framework provides technical support for the application-scenario-adaptive framework，and the application-scenario-adaptive framework guides the direction of technical optimization，thus forming a complete detection system covering the entire process of forensic evidence authentication. In response to the evidentiary credibility challenges posed by deepfake facial images as a novel criminal vector，this study argues that forensic examiners should facilitate the translation of detection outcomes into forensic authentication，integrating detection results with the Bayesian inference framework to enhance their admissibility and probative force in judicial proceedings. Specifically，a Bayesian inference-based forensic authentication model is proposed. Technical detection results are taken as the prior probability，forensic examiners’ professional experience and case context are integrated to determine the likelihood ratio，and the posterior probability of the authenticity of facial images is ultimately calculated via the Bayesian formula to convert objective technical indicators into credible judicial authentication conclusions. Furthermore，forensic examiners should continuously improve their understanding of deepfake technologies，master the working principles and limitations of detection technologies，and avoid over-reliance on technical detection results to ensure the scientificity and rigor of forensic authentication. In conclusion，by bridging the advancements in computer vision technology with the practical demands of forensic evidence practice，this research articulates the logical pathway from technical detection to judicial authentication，providing a theoretically insightful and practically relevant reference for forensic science researchers and judicial practitioners alike. For forensic science researchers，this study clarifies the research direction of integrating technical research with judicial practice，identifies the key issues to be addressed in the future （such as the construction of forensic-oriented datasets，the optimization of detection algorithms adapted to judicial scenarios，and the formulation of forensic identification standards），and offers a theoretical framework for subsequent research. For judicial practitioners，this study provides a practical operational path for the forensic authentication of deepfake facial images，facilitates the better grasp of the application methods and precautions of deepfake detection technologies，and elevates the efficiency and accuracy of digital evidence authentication. Additionally，this study offers a reference for the formulation of relevant laws and regulations，which helps improve the legal system of digital evidence authentication and promote the sound development of the criminal justice system in the era of deepfake technology.
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963002869284869, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, xref=null, ext=[AuthorCompanyExt(id=1322963002877673478, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, companyId=1322963002869284869, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Criminal Investigation，People’s Public Security University of China，Beijing 100038，China), AuthorCompanyExt(id=1322963002886062087, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, companyId=1322963002869284869, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国人民公安大学侦查学院，北京 100038)])])], keywords=[Keyword(id=1322963003666202647, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, orderNo=1, keyword=forensic science), Keyword(id=1322963003758477336, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, orderNo=2, keyword=evidence), Keyword(id=1322963003825586201, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, orderNo=3, keyword=facial image), Keyword(id=1322963003896889370, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, orderNo=4, keyword=deepfake), Keyword(id=1322963003959803931, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, orderNo=5, keyword=detection), Keyword(id=1322963004022718492, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, orderNo=6, keyword=identification), Keyword(id=1322963004114993181, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, orderNo=1, keyword=司法), Keyword(id=1322963004182102046, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, orderNo=2, keyword=证据), Keyword(id=1322963004245016607, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, orderNo=3, keyword=人脸图像), Keyword(id=1322963004312125472, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, orderNo=4, keyword=深度伪造), Keyword(id=1322963004370845729, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, orderNo=5, keyword=检测), Keyword(id=1322963004437954594, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, orderNo=6, keyword=鉴定)], refs=[Reference(id=1322963009307541578, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=3632, pageEnd=3637, url=null, language=null, rfNumber=null, rfOrder=0, authorNames=Amundsen A E, Ovens K M, journalName=null, refType=null, unstructuredReference=AmundsenA E and OvensK M. 2017. Forensics analysis of WI-FI communication traces in mobile devices//Proceedings of 2017 IEEE International Conference on Big Data （Big Data）. Boston，USA： IEEE： 3632-3637 ［DOI： 10.1109/BigData.2017.8258357］, articleTitle=Forensics analysis of WI-FI communication traces in mobile devices, refAbstract=null), Reference(id=1322963009387233355, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=252, issue=null, pageStart=null, pageEnd=124260, url=null, language=null, rfNumber=null, rfOrder=1, authorNames=Abbas F, Taeihagh A, journalName=Expert Systems with Applications, refType=null, unstructuredReference=AbbasF and TaeihaghA. 2024. Unmasking deepfakes： a systematic review of deepfake detection and generation techniques using artificial intelligence. Expert Systems with Applications，252： #124260 ［DOI： 10.1016/j.eswa.2024.124260］, articleTitle=Unmasking deepfakes： a systematic review of deepfake detection and generation techniques using artificial intelligence, refAbstract=null), Reference(id=1322963009458536524, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=73, issue=null, pageStart=null, pageEnd=103111, url=null, language=null, rfNumber=null, rfOrder=2, authorNames=Agudo M M, Fantinato C, Roseth A, Aanes H, Gill P, Fonneløp A E, journalName=Forensic Science International： Genetics, refType=null, unstructuredReference=AgudoM M，FantinatoC，RosethA，AanesH，GillP，FonneløpA E，et al. 2024. A comparison of likelihood ratios calculated from surface DNA mixtures using MPS and CE technologies. Forensic Science International： Genetics，73： #103111 ［DOI： 10.1016/j.fsigen.2024.103111］, articleTitle=A comparison of likelihood ratios calculated from surface DNA mixtures using MPS and CE technologies, refAbstract=null), Reference(id=1322963009546616909, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2022, volume=21, issue=1, pageStart=18, pageEnd=24, url=null, language=null, rfNumber=null, rfOrder=3, authorNames=Alhajjar E, Lee K, journalName=European Conference on Cyber Warfare and Security, refType=null, unstructuredReference=AlhajjarE and LeeK. 2022. The U.S. cyber threat landscape. European Conference on Cyber Warfare and Security，21（1）： 18-24 ［DOI： 10.34190/eccws.21.1.197］, articleTitle=The U.S. cyber threat landscape, refAbstract=null), Reference(id=1322963011190784078, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=5, pageStart=20, pageEnd=35, url=null, language=null, rfNumber=null, rfOrder=4, authorNames=Almars A M, journalName=Journal of Computer and Communications, refType=null, unstructuredReference=AlmarsA M. 2021. Deepfakes detection techniques using deep learning： a survey. Journal of Computer and Communications，9（5）： 20-35 ［DOI： 10.4236/jcc.2021.95003］, articleTitle=Deepfakes detection techniques using deep learning： a survey, refAbstract=null), Reference(id=1322963011291447375, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2023, volume=11, issue=null, pageStart=16711, pageEnd=16722, url=null, language=null, rfNumber=null, rfOrder=5, authorNames=Alnaim N M, Almutairi Z M, Alsuwat M S, Alalawi H H, Alshobaili A, Alenezi F S, journalName=IEEE Access, refType=null, unstructuredReference=AlnaimN M，AlmutairiZ M，AlsuwatM S，AlalawiH H，AlshobailiA and AleneziF S. 2023. DFFMD： a deepfake face mask dataset for infectious disease era with deepfake detection algorithms. IEEE Access，11： 16711-16722 ［DOI： 10.1109/ACCESS.2023.3246661］, articleTitle=DFFMD： a deepfake face mask dataset for infectious disease era with deepfake detection algorithms, refAbstract=null), Reference(id=1322963011408887888, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2026, volume=23, issue=null, pageStart=null, pageEnd=100819, url=null, language=null, rfNumber=null, rfOrder=6, authorNames=Bharati N, Wong P, Mostéfaoui S K, Kbaier D, Collie J, journalName=Machine Learning with Applications, refType=null, unstructuredReference=BharatiN，WongP，MostéfaouiS K，KbaierD and CollieJ. 2026. Explainable deepfake detection： a multi-model framework with human-interpretable rationales for legal investigation purposes. Machine Learning with Applications，23： #100819 ［DOI： 10.1016/j.mlwa.2025.100819］, articleTitle=Explainable deepfake detection： a multi-model framework with human-interpretable rationales for legal investigation purposes, refAbstract=null), Reference(id=1322963011501162577, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2206.12043.pdf, language=null, rfNumber=null, rfOrder=7, authorNames=Bohček M and Farid H, journalName=null, refType=null, unstructuredReference=Bohček M and FaridH. 2022. Protecting President Zelenskyy against deep fakes ［EB/OL］. ［2026-01-10］., articleTitle=Protecting President Zelenskyy against deep fakes, refAbstract=null), Reference(id=1322963011580854354, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2023, volume=9, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=8, authorNames=Bray S D, Johnson S D, Kleinberg B, journalName=Journal of Cyber Security, refType=null, unstructuredReference=BrayS D，JohnsonS D and KleinbergB. 2023. Testing human ability to detect “deepfake” images of human faces. Journal of Cyber Security，9（1） ［DOI： 10.1093/cybsec/tyad011］, articleTitle=Testing human ability to detect “deepfake” images of human faces, refAbstract=null), Reference(id=1322963011647963219, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=14, issue=1, pageStart=null, pageEnd=2, url=null, language=null, rfNumber=null, rfOrder=9, authorNames=Brown A, Johnson S D, Tuptuk N, journalName=Crime Science, refType=null, unstructuredReference=BrownA，JohnsonS D and TuptukN. 2025. A scoping study： crime and connected and autonomous vehicles. Crime Science，14（1）： #2 ［DOI： 10.1186/s40163-025-00245-x］, articleTitle=A scoping study： crime and connected and autonomous vehicles, refAbstract=null), Reference(id=1322963011715072084, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=24, issue=2, pageStart=null, pageEnd=2550001, url=null, language=null, rfNumber=null, rfOrder=10, authorNames=Bunluesakdikul P, Mahanan W, Sungunnasil P, Sangamuang S, journalName=International Journal of Computational Intelligence and Applications, refType=null, unstructuredReference=BunluesakdikulP，MahananW，SungunnasilP and SangamuangS. 2025. Deepfake video detection： a novel approach via NLP-based classification. International Journal of Computational Intelligence and Applications，24（2）： #2550001 ［DOI： 10.1142/S1469026825500014］, articleTitle=Deepfake video detection： a novel approach via NLP-based classification, refAbstract=null), Reference(id=1322963011803152469, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=null, rfOrder=11, authorNames=Cai Z, Stefanov K, Dhall A, Hayat M, journalName=Do you really mean that？ Content driven audio-visual deepfake dataset and multimodal method for temporal forgery localization/, refType=null, unstructuredReference=CaiZ，StefanovK，DhallA and HayatM. 2022. Do you really mean that？ Content driven audio-visual deepfake dataset and multimodal method for temporal forgery localization//Proceedings of 2022 International Conference on Digital Image Computing： Techniques and Applications （DICTA）： 1-10 ［DOI： 10.1109/DICTA56598.2022.10034605］, articleTitle=2022, refAbstract=null), Reference(id=1322963011874455638, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=4871, pageEnd=4874, url=null, language=null, rfNumber=null, rfOrder=12, authorNames=Çiftçi U A and Demir İ, journalName=2023 IEEE International Geoscience and Remote Sensing Symposium （IGARSS）, refType=null, unstructuredReference=Çiftçi U A and Demirİ. 2023. Deepfake satellite imagery detection with multi-attention and super resolution//2023 IEEE International Geoscience and Remote Sensing Symposium （IGARSS）. Pasadena，USA： IEEE： 4871-4874 ［DOI： 10.1109/IGARSS52108.2023.10282927］, articleTitle=Deepfake satellite imagery detection with multi-attention and super resolution, refAbstract=null), Reference(id=1322963011945758807, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=null, rfOrder=13, authorNames=Dagar D, Vishwakarma D K, journalName=null, refType=null, unstructuredReference=DagarD and VishwakarmaD K. 2023. Div-Df： a diverse manipulation deepfake video dataset//Proceedings of 2023 Global Conference on Information Technologies and Communications （GCITC）. Bangalore，India： IEEE： 1-6 ［DOI： 10.1109/GCITC60406.2023.10426446］, articleTitle=Div-Df： a diverse manipulation deepfake video dataset, refAbstract=null), Reference(id=1322963012025450584, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=14, authorNames=Dayal S B and van Niekerk B, journalName=null, refType=null, unstructuredReference=Dayal S B and van Niekerk B. 2021. Deepfake video detection//Proceedings of the 20th European Conference on Cyber Warfare and Security. 2021 ［DOI： 10.34190/ECCWS.21.110］, articleTitle=Deepfake video detection, refAbstract=null), Reference(id=1322963012100948057, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=31, issue=6, pageStart=null, pageEnd=410, url=null, language=null, rfNumber=null, rfOrder=15, authorNames=Deng L W, Wu B D, Wang J D, journalName=Multimedia Systems, refType=null, unstructuredReference=DengL W，WuB D and WangJ D. 2025. A multi-label classification method combined with texture enhancement for deepfake face detection. Multimedia Systems，31（6）： #410 ［DOI： 10.1007/s00530-025-01996-y］, articleTitle=A multi-label classification method combined with texture enhancement for deepfake face detection, refAbstract=null), Reference(id=1322963012172251226, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=16, authorNames=Deng W, Feng J, Huang D, Kan M, Sun Z, Zheng F, journalName=null, refType=null, unstructuredReference=DengW，FengJ，HuangD，KanM，SunZ，ZhengF，et al. 2022. Biometric recognition//Proceedings of the 16th Chinese Conference on Biometrics Recognition（CCBR）. Beijing，China： ［s.n.］ ［DOI： 10.1007/978-3-031-20233-9］, articleTitle=Biometric recognition, refAbstract=null), Reference(id=1322963012285497435, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=2, pageStart=295, pageEnd=317, url=null, language=null, rfNumber=null, rfOrder=17, authorNames=Ding F, Kuang R S, Zhou Y, Sun L, Zhu X G, Zhu G P, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=DingF，KuangR S，ZhouY，SunL，ZhuX G and ZhuG P. 2024. A survey of Deepfake and related digital forensics. Journal of Image and Graphics，29（2）： 295-317, articleTitle=A survey of Deepfake and related digital forensics, refAbstract=null), Reference(id=1322963012352606300, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=2, pageStart=295, pageEnd=317, url=null, language=null, rfNumber=null, rfOrder=18, authorNames=丁峰, 匡仁盛, 周越, 孙珑, 朱小刚, 朱国普, journalName=中国图象图形学报, refType=null, unstructuredReference=丁峰，匡仁盛，周越，孙珑，朱小刚，朱国普. 2024. 深度伪造及其取证技术综述. 中国图象图形学报，29（2）： 295-317 ［DOI： 10.11834/jig.230088］, articleTitle=深度伪造及其取证技术综述, refAbstract=null), Reference(id=1322963012423909469, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2006.07397.pdf, language=null, rfNumber=null, rfOrder=19, authorNames=Dolhansky B, Bitton J, Pflaum B, Lu J, Howes R, Wang M, journalName=null, refType=null, unstructuredReference=DolhanskyB，BittonJ，PflaumB，LuJ，HowesR，WangM，et al. 2020. The DeepFake detection challenge （DFDC） dataset ［EB/OL］. ［2026-01-10］., articleTitle=The DeepFake detection challenge （DFDC） dataset, refAbstract=null), Reference(id=1322963012507795550, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2023, volume=18, issue=null, pageStart=2596, pageEnd=2608, url=null, language=null, rfNumber=null, rfOrder=20, authorNames=Dong J H, Wang Y, Lai J H, Xie X H, journalName=IEEE Transactions on Information Forensics and Security, refType=null, unstructuredReference=DongJ H，WangY，LaiJ H and XieX H. 2023. Restricted black-box adversarial attack against DeepFake face swapping. IEEE Transactions on Information Forensics and Security，18： 2596-2608 ［DOI： 10.1109/TIFS.2023.3266702］, articleTitle=Restricted black-box adversarial attack against DeepFake face swapping, refAbstract=null), Reference(id=1322963012616847455, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=625, issue=7996, pageStart=844, pageEnd=848, url=null, language=null, rfNumber=null, rfOrder=21, authorNames=Eisenstein M, journalName=Nature, refType=null, unstructuredReference=EisensteinM. 2024. Seven technologies to watch in 2024. Nature，625（7996）： 844-848 ［DOI： 10.1038/d41586-024-00173-x］, articleTitle=Seven technologies to watch in 2024, refAbstract=null), Reference(id=1322963012688150624, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=null, rfOrder=22, authorNames=Galdi C, Panariello M, Todisco M, Evans N, journalName=null, refType=null, unstructuredReference=GaldiC，PanarielloM，TodiscoM and EvansN. 2024. 2D-malafide： adversarial attacks against face deepfake detection systems//Proceedings of 2024 International Conference of the Biometrics Special Interest Group （BIOSIG）. Darmstadt，Germany： IEEE： 1-7 ［DOI： 10.1109/BIOSIG61931.2024.10786754］, articleTitle=2D-malafide： adversarial attacks against face deepfake detection systems, refAbstract=null), Reference(id=1322963012759453793, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=259, issue=null, pageStart=1737, pageEnd=1748, url=null, language=null, rfNumber=null, rfOrder=23, authorNames=Garg D, Gill R, journalName=null, refType=null, unstructuredReference=GargD and GillR. 2025. Unmasking deepfakes： a review of current datasets，tools，and detection features//Proceedings of the 6th International Conference on Futuristic Trends in Networks and Computing Technologies （FTNCT06），Held in Uttarakhand，India，259： 1737-1748 ［DOI： 10.1016/j.procs.2025.04.129］, articleTitle=Unmasking deepfakes： a review of current datasets，tools，and detection features, refAbstract=null), Reference(id=1322963012834951266, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=40, issue=2, pageStart=397, pageEnd=412, url=null, language=null, rfNumber=null, rfOrder=24, authorNames=Ge J W, Cao J X, Zhao Z X, Liu B, journalName=Journal of Computer Science and Technology, refType=null, unstructuredReference=GeJ W，CaoJ X，ZhaoZ X and LiuB. 2025. FSD-GAN： generative adversarial training for face swap detection via the latent noise fingerprint. Journal of Computer Science and Technology，40（2）： 397-412［DOI： 10.1007/s11390-024-3337-8］, articleTitle=FSD-GAN： generative adversarial training for face swap detection via the latent noise fingerprint, refAbstract=null), Reference(id=1322963012902060131, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=274, pageEnd=288, url=null, language=null, rfNumber=null, rfOrder=25, authorNames=Guan W N, Wang W, Peng B, Dong J, Tan T N, journalName=null, refType=null, unstructuredReference=GuanW N，WangW，PengB，DongJ and TanT N. 2025. ST-SBV： spatial-temporal self-blended videos for deepfake detection//Proceedings of the 7th Chinese Conference on Pattern Recognition and Computer Vision. Urumqi，China： Springer： 274-288 ［DOI： 10.1007/978-981-97-8620-6_19］, articleTitle=ST-SBV： spatial-temporal self-blended videos for deepfake detection, refAbstract=null), Reference(id=1322963012969168996, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=4358, pageEnd=4367, url=null, language=null, rfNumber=null, rfOrder=26, authorNames=He Y, Gan B, Chen S, Zhou Y, Yin G, Song L, journalName=null, refType=null, unstructuredReference=HeY，GanB，ChenS，ZhouY，YinG，SongL，et al. 2021. ForgeryNet： a versatile benchmark for comprehensive forgery analysis//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Nashville，TN，USA： IEEE： 4358-4367 ［DOI： 10.1109/CVPR46437.2021.00434］, articleTitle=ForgeryNet： a versatile benchmark for comprehensive forgery analysis, refAbstract=null), Reference(id=1322963013053055077, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=null, rfOrder=27, authorNames=Huang D Z, Zhang Y Q, journalName=null, refType=null, unstructuredReference=HuangD Z and ZhangY Q. 2024. Learning meta model for strong generalization deepfake detection//Proceedings of 2024 International Joint Conference on Neural Networks. Yokohama，Japan： IEEE： 1-8 ［DOI： 10.1109/IJCNN60899.2024.10651482］, articleTitle=Learning meta model for strong generalization deepfake detection, refAbstract=null), Reference(id=1322963013136941158, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=null, rfOrder=28, authorNames=Iqbal A, Olegård J, Ghimire R, journalName=null, refType=null, unstructuredReference=IqbalA，OlegårdJ and GhimireR. 2020. Digital forensic evidence—the missing link in threat modeling//Proceedings of 2020 International Conference on Data Analytics for Business and Industry： Way Towards a Sustainable Economy （ICDABI）. Sakheer，Bahrain： IEEE： 1-5 ［DOI： 10.1109/ICDABI51230.2020.9325650］, articleTitle=Digital forensic evidence—the missing link in threat modeling, refAbstract=null), Reference(id=1322963013216632935, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=null, rfOrder=29, authorNames=Joel E J, Kumar K P, Silar M M, Rohan J, journalName=null, refType=null, unstructuredReference=JoelE J，KumarK P，SilarM M and RohanJ. 2025. Flexible multi-modality deepfake identification with dynamic learning and cross-modality inconsistency//Proceedings of the 3rd International Conference on Advancements in Electrical，Electronics，Communication，Computing and Automation （ICAECA 2025）. Coimbatore，India： IEEE： 1-6 ［DOI： 10.1109/ICAECA63854.2025.11012276］, articleTitle=Flexible multi-modality deepfake identification with dynamic learning and cross-modality inconsistency, refAbstract=null), Reference(id=1322963013292130408, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=112, issue=null, pageStart=null, pageEnd=103146, url=null, language=null, rfNumber=null, rfOrder=30, authorNames=Ji S, journalName=Women’s Studies International Forum, refType=null, unstructuredReference=JiS. 2025. #MeToo in an AI-generated deepfake sexual violence era in South Korea. Women’s Studies International Forum，112： #103146 ［DOI： 10.1016/j.wsif.2025.103146］, articleTitle=#MeToo in an AI-generated deepfake sexual violence era in South Korea, refAbstract=null), Reference(id=1322963013359239273, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=2356, pageEnd=2360, url=null, language=null, rfNumber=null, rfOrder=31, authorNames=Jia S, Li X, Lyu S, journalName=null, refType=null, unstructuredReference=JiaS，LiX and LyuS. 2022. Model attribution of face-swap deepfake videos//Proceedings of the 29th IEEE International Conference on Image Processing （ICIP）. Bordeaux，France： IEEE Computer Society： 2356-2360 ［DOI： 10.1109/ICIP46576.2022.9897972］, articleTitle=Model attribution of face-swap deepfake videos, refAbstract=null), Reference(id=1322963013426348138, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=2886, pageEnd=2895, url=null, language=null, rfNumber=null, rfOrder=32, authorNames=Jiang L, Li R, Wu W, Qian C, Loy C C, journalName=null, refType=null, unstructuredReference=JiangL，LiR，WuW，QianC and LoyC C. 2020. DeeperForensics-1.0： a large-scale dataset for real-world face forgery detection//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle，USA： IEEE： 2886-2895 ［DOI： 10.1109/CVPR42600.2020.00296］, articleTitle=DeeperForensics-1.0： a large-scale dataset for real-world face forgery detection, refAbstract=null), Reference(id=1322963013506039915, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=49, issue=null, pageStart=null, pageEnd=301747, url=null, language=null, rfNumber=null, rfOrder=33, authorNames=Jin X, Wu N, Jiang Q, Kou Y R, Duan H X, Wang P M, journalName=Forensic Science International： Digital Investigation, refType=null, unstructuredReference=JinX，WuN，JiangQ，KouY R，DuanH X，WangP M，et al. 2024. A dual descriptor combined with frequency domain reconstruction learning for face forgery detection in deepfake videos. Forensic Science International： Digital Investigation，49： #301747 ［DOI： 10.1016/j.fsidi.2024.301747］, articleTitle=A dual descriptor combined with frequency domain reconstruction learning for face forgery detection in deepfake videos, refAbstract=null), Reference(id=1322963013573148780, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2021, volume=2021, issue=1, pageStart=null, pageEnd=6626974, url=null, language=null, rfNumber=null, rfOrder=34, authorNames=Jin X L, Ye D P, Chen C X, journalName=Security and Communication Networks, refType=null, unstructuredReference=JinX L，YeD P and ChenC X. 2021. Countering spoof： towards detecting deepfake with multidimensional biological signals. Security and Communication Networks，2021（1）： #6626974 ［DOI： 10.1155/2021/6626974］, articleTitle=Countering spoof： towards detecting deepfake with multidimensional biological signals, refAbstract=null), Reference(id=1322963013661229165, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=4643, pageEnd=4653, url=null, language=null, rfNumber=null, rfOrder=35, authorNames=Ju Y, Hu S, Jia S, Chen G H, Lyu S W, journalName=null, refType=null, unstructuredReference=JuY，HuS，JiaS，ChenG H and LyuS W. 2024. Improving fairness in deepfake detection//Proceedings of 2024 IEEE/CVF Winter Conference on Applications of Computer Vision （WACV）. Waikoloa，USA： IEEE： 4643-4653 ［DOI： 10.1109/WACV57701.2024.00459］, articleTitle=Improving fairness in deepfake detection, refAbstract=null), Reference(id=1322963013749309550, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=36, authorNames=Karras T, Aila T, Laine S, Lehtinen J, journalName=null, refType=null, unstructuredReference=KarrasT，AilaT，LaineS and LehtinenJ. 2018. Progressive growing of GANs for improved quality，stability，and variation//Proceedings of the 6th International Conference on Learning Representations （ICLR）. Vancouver， Canada： ICLR, articleTitle=Progressive growing of GANs for improved quality, refAbstract=null), Reference(id=1322963013812224111, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=4396, pageEnd=4405, url=null, language=null, rfNumber=null, rfOrder=37, authorNames=Karras T, Laine S, Aila T, journalName=null, refType=null, unstructuredReference=KarrasT，LaineS and AilaT. 2019. A style-based generator architecture for generative adversarial networks//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Beach，USA： IEEE： 4396-4405 ［DOI： 10.1109/CVPR.2019.00453］, articleTitle=A style-based generator architecture for generative adversarial networks, refAbstract=null), Reference(id=1322963013896110192, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=57, issue=8, pageStart=null, pageEnd=202, url=null, language=null, rfNumber=null, rfOrder=38, authorNames=Kaur M, Saini M, journalName=Artificial Intelligence Review, refType=null, unstructuredReference=KaurM and SainiM. 2024. Role of artificial intelligence in the crime prediction and pattern analysis studies published over the last decade： a scientometric analysis. Artificial Intelligence Review，57（8）： #202 ［DOI： 10.1007/s10462-024-10823-1］, articleTitle=Role of artificial intelligence in the crime prediction and pattern analysis studies published over the last decade： a scientometric analysis, refAbstract=null), Reference(id=1322963013963219057, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2108.05080.pdf, language=null, rfNumber=null, rfOrder=39, authorNames=Khalid H, Tariq S, Kim M, Woo S S, journalName=null, refType=null, unstructuredReference=KhalidH，TariqS，KimM and WooS S. 2021. FakeAVCeleb： a novel audio-video multimodal deepfake dataset ［EB/OL］. ［2026-01-10］., articleTitle=FakeAVCeleb： a novel audio-video multimodal deepfake dataset, refAbstract=null), Reference(id=1322963015645134962, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=675, pageEnd=680, url=null, language=null, rfNumber=null, rfOrder=40, authorNames=Khan S S, Hossain R, Bishal S H, Khan R, journalName=null, refType=null, unstructuredReference=KhanS S，HossainR，BishalS H and KhanR. 2024. Smartphone-based deepfake detection through transfer learning and lightweight knowledge distillation technique//Proceedings of the 27th International Conference on Computer and Information Technology （ICCIT）. Cox’s Bazar，Bangladesh： IEEE： 675-680 ［DOI： 10.1109/ICCIT64611.2024.11022522］, articleTitle=Smartphone-based deepfake detection through transfer learning and lightweight knowledge distillation technique, refAbstract=null), Reference(id=1322963015745798259, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=null, rfOrder=41, authorNames=Khodabakhsh A, Ramachandra R, Raja K, Wasnik P, Busch C, journalName=null, refType=null, unstructuredReference=KhodabakhshA，RamachandraR，RajaK，WasnikP and BuschC. 2018. Fake face detection methods： can they Be generalized?//Proceedings of 2018 International Conference of the Biometrics Special Interest Group （BIOSIG）. Darmstadt，Germany： IEEE： 1-6 ［DOI： 10.23919/BIOSIG.2018.8553251］, articleTitle=Fake face detection methods： can they Be generalized?, refAbstract=null), Reference(id=1322963015884210292, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/1812.08685.pdf, language=null, rfNumber=null, rfOrder=42, authorNames=Korshunov P, Marcel S, journalName=null, refType=null, unstructuredReference=KorshunovP and MarcelS. 2018. DeepFakes： a new threat to face recognition？ Assessment and detection ［EB/OL］. ［2026-01-10］., articleTitle=DeepFakes： a new threat to face recognition？, refAbstract=null), Reference(id=1322963015951319157, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=W9, issue=2025, pageStart=169, pageEnd=174, url=null, language=null, rfNumber=null, rfOrder=43, authorNames=Krasilnikov M, Nikitin M, Konushin A, journalName=The International Archives of the Photogrammetry，Remote Sensing and Spatial Information Sciences，XLVIII-2/, refType=null, unstructuredReference=KrasilnikovM，NikitinM and KonushinA. 2025. VCF： a real-world video conference deepfake benchmark for face-swap detection and robustness evaluation. The International Archives of the Photogrammetry，Remote Sensing and Spatial Information Sciences，XLVIII-2/W9-2025： 169-174 ［DOI： 10.5194/isprs-archives-XLVIII-2-W9-2025-169-2025］, articleTitle=VCF： a real-world video conference deepfake benchmark for face-swap detection and robustness evaluation, refAbstract=null), Reference(id=1322963016014233718, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=153, issue=2, pageStart=null, pageEnd=2023063954, url=null, language=null, rfNumber=null, rfOrder=44, authorNames=Krishna S, Dubrosa F, Milanaik R, journalName=Pediatrics, refType=null, unstructuredReference=KrishnaS，DubrosaF and MilanaikR. 2024. Rising threats of AI-driven child sexual abuse material. Pediatrics，153（2）： #2023063954 ［DOI： 10.1542/peds.2023-063954］, articleTitle=Rising threats of AI-driven child sexual abuse material, refAbstract=null), Reference(id=1322963016081342583, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=10724, pageEnd=10733, url=null, language=null, rfNumber=null, rfOrder=45, authorNames=Kwon P, You J, Nam G, Park S, Chae G, journalName=null, refType=null, unstructuredReference=KwonP，YouJ，NamG，ParkS and ChaeG. 2021. KoDF： a large-scale Korean DeepFake detection dataset//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision （ICCV）. Montreal，QC，Canada： IEEE： 10724-10733 ［DOI： 10.1109/ICCV48922.2021.01057］, articleTitle=KoDF： a large-scale Korean DeepFake detection dataset, refAbstract=null), Reference(id=1322963016148451448, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2107.14480.pdf, language=null, rfNumber=null, rfOrder=46, authorNames=Le T N, Nguyen H H, Yamagishi J, Echizen I, journalName=null, refType=null, unstructuredReference=LeT N，NguyenH H，YamagishiJ and EchizenI. 2021. OpenForensics： large-scale challenging dataset for multi-face forgery detection and segmentation In-the-wild ［EB/OL］. ［2026-01-10］., articleTitle=OpenForensics： large-scale challenging dataset for multi-face forgery detection and segmentation In-the-wild, refAbstract=null), Reference(id=1322963016215560313, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=15, issue=12, pageStart=null, pageEnd=6588, url=null, language=null, rfNumber=null, rfOrder=47, authorNames=Lei S Z, Song J F, Feng F Y, Yan Z Y, Wang A X, journalName=Applied Sciences, refType=null, unstructuredReference=LeiS Z，SongJ F，FengF Y，YanZ Y and WangA X. 2025. Deepfake face detection and adversarial attack defense method based on multi-feature decision fusion. Applied Sciences，15（12）： #6588 ［DOI： 10.3390/app15126588］, articleTitle=Deepfake face detection and adversarial attack defense method based on multi-feature decision fusion, refAbstract=null), Reference(id=1322963016274280570, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=36, issue=1, pageStart=1, pageEnd=32, url=null, language=null, rfNumber=null, rfOrder=48, authorNames=Levanon L, Tully G, journalName=Criminal Law Forum, refType=null, unstructuredReference=LevanonL and TullyG. 2025. Fingerprint analysis and reporting in legal trials： a critical re-evaluation. Criminal Law Forum，36（1）： 1-32 ［DOI： 10.1007/s10609-025-09497-3］, articleTitle=Fingerprint analysis and reporting in legal trials： a critical re-evaluation, refAbstract=null), Reference(id=1322963016337195131, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2019, volume=24, issue=10, pageStart=1761, pageEnd=1771, url=null, language=null, rfNumber=null, rfOrder=49, authorNames=Li Q Y, Ji Q G, Hong S D, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=LiQ Y，JiQ G and HongS D. 2019. FastFace： a real-time robust algorithm for face detection. Journal of Image and Graphics，24（10）： 1761-1771, articleTitle=FastFace： a real-time robust algorithm for face detection, refAbstract=null), Reference(id=1322963016412692604, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2019, volume=24, issue=10, pageStart=1761, pageEnd=1771, url=null, language=null, rfNumber=null, rfOrder=50, authorNames=李启运, 纪庆革, 洪赛丁, journalName=中国图象图形学报, refType=null, unstructuredReference=李启运，纪庆革，洪赛丁. 2019. FastFace： 实时鲁棒的人脸检测算法. 中国图象图形学报，24（10）： 1761-1771 ［DOI： 10.11834/jig.180662］, articleTitle=FastFace： 实时鲁棒的人脸检测算法, refAbstract=null), Reference(id=1322963016471412861, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=3204, pageEnd=3213, url=null, language=null, rfNumber=null, rfOrder=51, authorNames=Li Y, Yang X, Sun P, Qi H, Lyu S, journalName=null, refType=null, unstructuredReference=LiY，YangX，SunP，QiH and LyuS. 2020. Celeb-DF： a large-scale challenging dataset for DeepFake forensics//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle，USA： IEEE： 3204-3213 ［DOI： 10.1109/CVPR42600.2020.00327］, articleTitle=Celeb-DF： a large-scale challenging dataset for DeepFake forensics, refAbstract=null), Reference(id=1322963016542716030, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/1909.12962.pdf, language=null, rfNumber=null, rfOrder=52, authorNames=Li Y Z, Yang X, Sun P, Qi H G, Lyu S W, journalName=null, refType=null, unstructuredReference=LiY Z，YangX，SunP，QiH G and LyuS W. 2019. Celeb-DF： a large-scale challenging dataset for DeepFake forensics ［EB/OL］. ［2026-01-10］., articleTitle=Celeb-DF： a large-scale challenging dataset for DeepFake forensics, refAbstract=null), Reference(id=1322963016689516671, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2023, volume=159, issue=null, pageStart=34, pageEnd=42, url=null, language=null, rfNumber=null, rfOrder=53, authorNames=Liang B Y, Wang Z Y, Huang B J, Zou Q, Wang Q, Liang J J, journalName=Neural Networks, refType=null, unstructuredReference=LiangB Y，WangZ Y，HuangB J，ZouQ，WangQ and LiangJ J. 2023. Depth map guided triplet network for deepfake face detection. Neural Networks，159： 34-42 ［DOI： 10.1016/j.neunet.2022.11.031］, articleTitle=Depth map guided triplet network for deepfake face detection, refAbstract=null), Reference(id=1322963016752431232, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=12, issue=null, pageStart=180135, pageEnd=180145, url=null, language=null, rfNumber=null, rfOrder=54, authorNames=Liu X Y, Song P C, Lu P, Wang Y J, journalName=IEEE Access, refType=null, unstructuredReference=LiuX Y，SongP C，LuP and WangY J. 2024. Meta-learning with relation embedding for few-shot deepfake detection. IEEE Access，12： 180135-180145 ［DOI： 10.1109/ACCESS.2024.3499353］, articleTitle=Meta-learning with relation embedding for few-shot deepfake detection, refAbstract=null), Reference(id=1322963016815345793, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=356, issue=null, pageStart=null, pageEnd=111967, url=null, language=null, rfNumber=null, rfOrder=55, authorNames=Ma X, Luo Y P, Yu Y, Liu Y W, Li S, Li H M, journalName=Forensic Science International, refType=null, unstructuredReference=MaX，LuoY P，YuY，LiuY W，LiS and LiH M. 2024. Similarity quantification of bare footprint based on linear measurement and shape context contour combined score-based likelihood ratio evaluation. Forensic Science International，356： #111967 ［DOI： 10.1016/j.forsciint.2024.111967］, articleTitle=Similarity quantification of bare footprint based on linear measurement and shape context contour combined score-based likelihood ratio evaluation, refAbstract=null), Reference(id=1322963016878260354, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=8, issue=null, pageStart=null, pageEnd=100458, url=null, language=null, rfNumber=null, rfOrder=56, authorNames=Macarulla Rodriguez A, Geradts Z, Worring M, Unzueta L, journalName=Forensic Science International： Synergy, refType=null, unstructuredReference=Macarulla RodriguezA，GeradtsZ，WorringM and UnzuetaL. 2024. Improved likelihood ratios for face recognition in surveillance video by multimodal feature pairing. Forensic Science International： Synergy，8： #100458 ［DOI： 10.1016/j.fsisyn.2024.100458］, articleTitle=Improved likelihood ratios for face recognition in surveillance video by multimodal feature pairing, refAbstract=null), Reference(id=1322963016945369219, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=1, pageEnd=20, url=null, language=null, rfNumber=null, rfOrder=57, authorNames=Mittal G, Hegde C, Memon N, journalName=Proceedings of, refType=null, unstructuredReference=MittalG，HegdeC and MemonN. 2024. Gotcha： real-time video deepfake detection via challenge-response//Proceedings of 2024 IEEE 9th European Symposium on Security and Privacy （EuroS&P）： 1-20 ［DOI： 10.1109/EuroSP60621.2024.00009］, articleTitle=Gotcha： real-time video deepfake detection via challenge-response, refAbstract=null), Reference(id=1322963017008283780, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2011, volume=53, issue=2, pageStart=242, pageEnd=256, url=null, language=null, rfNumber=null, rfOrder=58, authorNames=Morrison G S, journalName=Speech Communication, refType=null, unstructuredReference=MorrisonG S. 2011. A comparison of procedures for the calculation of forensic likelihood ratios from acoustic-phonetic data： multivariate kernel density （MVKD） versus Gaussian mixture model-universal background model （GMM-UBM）. Speech Communication，53（2）： 242-256 ［DOI： 10.1016/j.specom.2010.09.005］, articleTitle=A comparison of procedures for the calculation of forensic likelihood ratios from acoustic-phonetic data： multivariate kernel density （MVKD） versus Gaussian mixture model-universal background model （GMM-UBM）, refAbstract=null), Reference(id=1322963017075392645, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=null, rfOrder=59, authorNames=Narayan K, Agarwal H, Thakral K, Mittal S, Vatsa M, Singh R, journalName=null, refType=null, unstructuredReference=NarayanK，AgarwalH，ThakralK，MittalS，VatsaM and SinghR. 2022. DeePhy： on deepfake phylogeny//Proceedings of 2022 IEEE International Joint Conference on Biometrics （IJCB）. Dhabi，United Arab Emirates： IEEE： 1-10 ［DOI： 10.1109/IJCB54206.2022.10007968］, articleTitle=DeePhy： on deepfake phylogeny, refAbstract=null), Reference(id=1322963017142501510, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2020, volume=14, issue=5, pageStart=1038, pageEnd=1048, url=null, language=null, rfNumber=null, rfOrder=60, authorNames=Neves J C, Tolosana R, Vera-Rodriguez R, Lopes V, Proença H, Fierrez J, journalName=IEEE Journal of Selected Topics in Signal Processing, refType=null, unstructuredReference=NevesJ C，TolosanaR，Vera-RodriguezR，LopesV，ProençaH and FierrezJ. 2020. GANprintR： improved fakes and evaluation of the state of the art in face manipulation detection. IEEE Journal of Selected Topics in Signal Processing，14（5）： 1038-1048 ［DOI： 10.1109/JSTSP.2020.3007250］, articleTitle=GANprintR： improved fakes and evaluation of the state of the art in face manipulation detection, refAbstract=null), Reference(id=1322963017226387591, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=79, issue=3, pageStart=5295, pageEnd=5312, url=null, language=null, rfNumber=null, rfOrder=61, authorNames=Ni Y, Zeng W, Xia P, Yang G S, Tan R C, journalName=Computers，Materials and Continua, refType=null, unstructuredReference=NiY，ZengW，XiaP，YangG S and TanR C. 2024. A deepfake detection algorithm based on fourier transform of biological signal. Computers，Materials and Continua，79（3）： 5295-5312 ［DOI： 10.32604/cmc.2024.049911］, articleTitle=A deepfake detection algorithm based on fourier transform of biological signal, refAbstract=null), Reference(id=1322963017297690760, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=null, rfOrder=62, authorNames=Peng B, Fan H, Wang W, Dong J, Li Y, Lyu S, journalName=null, refType=null, unstructuredReference=PengB，FanH，WangW，DongJ，LiY and LyuS. 2021. DFGC 2021： a DeepFake game competition//Proceedings of 2021 IEEE International Joint Conference on Biometrics （IJCB）. Shenzhen，China： IEEE： 1-8 ［DOI： 10.1109/IJCB52358.2021.9484387］, articleTitle=DFGC 2021： a DeepFake game competition, refAbstract=null), Reference(id=1322963017385771145, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=492, pageEnd=508, url=null, language=null, rfNumber=null, rfOrder=63, authorNames=Peng B, Lyu S W, Wang W, Dong J, journalName=null, refType=null, unstructuredReference=PengB，LyuS W，WangW and DongJ. 2022. Counterfactual image enhancement for explanation of face swap deepfakes//Proceedings of the 5th Chinese Conference on Pattern Recognition and Computer Vision. Shenzhen，China： Springer： 492-508. Lecture Notes in Computer Science，#13535 ［DOI： 10.1007/978-3-031-18910-4_40］, articleTitle=Counterfactual image enhancement for explanation of face swap deepfakes, refAbstract=null), Reference(id=1322963017524183178, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=355, pageEnd=369, url=null, language=null, rfNumber=null, rfOrder=64, authorNames=Peng F, Zhang X L, Long M, journalName=null, refType=null, unstructuredReference=PengF，ZhangX L and LongM. 2023. F2DLNet： a face forgery detection and localization network based on SSIM error maps//Proceedings of the 4th International Conference on Machine Learning for Cyber Security. Guangzhou，China： Springer： 355-369 ［DOI： 10.1007/978-3-031-20099-1_30］, articleTitle=F2DLNet： a face forgery detection and localization network based on SSIM error maps, refAbstract=null), Reference(id=1322963017599680651, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2020, volume=29, issue=2, pageStart=503, pageEnd=532, url=null, language=null, rfNumber=null, rfOrder=65, authorNames=Pesetski A, journalName=The William and Mary Bill of Rights Journal, refType=null, unstructuredReference=PesetskiA. 2020. Deepfakes： a new content category for a digital age. The William and Mary Bill of Rights Journal，29（2）： 503-532, articleTitle=Deepfakes： a new content category for a digital age, refAbstract=null), Reference(id=1322963017687761036, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=7, pageStart=4654, pageEnd=4668, url=null, language=null, rfNumber=null, rfOrder=66, authorNames=Qiao T, Xie S C, Chen Y L, Retraint F, Luo X Y, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=QiaoT，XieS C，ChenY L，RetraintF and LuoX Y. 2024. Fully unsupervised deepfake video detection via enhanced contrastive learning. IEEE Transactions on Pattern Analysis and Machine Intelligence，46（7）： 4654-4668 ［DOI： 10.1109/TPAMI.2024.3356814］, articleTitle=Fully unsupervised deepfake video detection via enhanced contrastive learning, refAbstract=null), Reference(id=1322963017935224973, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=100099, url=null, language=null, rfNumber=null, rfOrder=67, authorNames=Ramanaharan R, Guruge D B, Agbinya J I, journalName=Data and Information Management, refType=null, unstructuredReference=RamanaharanR，GurugeD B and AgbinyaJ I. 2025. DeepFake video detection： insights into model generalisation — a systematic review. Data and Information Management： #100099 ［DOI： 10.1016/j.dim.2025.100099］, articleTitle=DeepFake video detection： insights into model generalisation — a systematic review, refAbstract=null), Reference(id=1322963018006528142, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=19, issue=1, pageStart=282, pageEnd=288, url=null, language=null, rfNumber=null, rfOrder=68, authorNames=Ramluckan T, journalName=International Conference on Cyber Warfare and Security, refType=null, unstructuredReference=RamluckanT. 2024. Deepfakes： the legal implications. International Conference on Cyber Warfare and Security，19（1）： 282-288 ［DOI： 10.34190/iccws.19.1.2099］, articleTitle=Deepfakes： the legal implications, refAbstract=null), Reference(id=1322963018102997135, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=15, issue=17, pageStart=null, pageEnd=9574, url=null, language=null, rfNumber=null, rfOrder=69, authorNames=Rosca C M, Stancu A, journalName=Applied Sciences, refType=null, unstructuredReference=RoscaC M and StancuA. 2025. AI anomaly-based deepfake detection using customized mahalanobis distance and head pose with facial landmarks. Applied Sciences，15（17）： #9574 ［DOI： 10.3390/app15179574］, articleTitle=AI anomaly-based deepfake detection using customized mahalanobis distance and head pose with facial landmarks, refAbstract=null), Reference(id=1322963018191077520, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=null, rfOrder=70, authorNames=Rössler A, Cozzolino D, Verdoliva L, Riess C, Thies J, Niessner M, journalName=null, refType=null, unstructuredReference=RösslerA，CozzolinoD，VerdolivaL，RiessC，ThiesJ and NiessnerM. 2019. FaceForensics++： learning to detect manipulated facial images//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul，Korea （South）： IEEE： 1-11 ［DOI： 10.1109/ICCV.2019.00009］, articleTitle=FaceForensics++： learning to detect manipulated facial images, refAbstract=null), Reference(id=1322963018258186385, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=119, issue=1, pageStart=71, pageEnd=90, url=null, language=null, rfNumber=null, rfOrder=71, authorNames=Schiff K J, Schiff D S, Bueno N S, journalName=American Political Science Review, refType=null, unstructuredReference=SchiffK J，SchiffD S and BuenoN S. 2025. The liar’s dividend： can politicians claim misinformation to evade accountability？ American Political Science Review，119（1）： 71-90 ［DOI： 10.1017/S0003055423001454］, articleTitle=The liar’s dividend： can politicians claim misinformation to evade accountability？, refAbstract=null), Reference(id=1322963018363043986, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2022, volume=513, issue=null, pageStart=351, pageEnd=371, url=null, language=null, rfNumber=null, rfOrder=72, authorNames=Seow J W, Lim M K, Phan R C W, Liu J K, journalName=Neurocomputing, refType=null, unstructuredReference=SeowJ W，LimM K，PhanR C W and LiuJ K. 2022. A comprehensive overview of deepfake： generation，detection，datasets，and opportunities. Neurocomputing，513： 351-371 ［DOI： 10.1016/j.neucom.2022.09.135］, articleTitle=A comprehensive overview of deepfake： generation，detection，datasets，and opportunities, refAbstract=null), Reference(id=1322963018442735763, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=55, issue=6, pageStart=973, pageEnd=982, url=null, language=null, rfNumber=null, rfOrder=73, authorNames=Shahzad S A, Hashmi A, Peng Y T, Tsao Y, Wang H M, journalName=IEEE Transactions on Human-Machine Systems, refType=null, unstructuredReference=ShahzadS A，HashmiA，PengY T，TsaoY and WangH M. 2025. AV-lip-sync+： leveraging AV-HuBERT to exploit multimodal inconsistency for deepfake detection of frontal face videos. IEEE Transactions on Human-Machine Systems，55（6）： 973-982 ［DOI： 10.1109/THMS.2025.3618409］, articleTitle=AV-lip-sync+： leveraging AV-HuBERT to exploit multimodal inconsistency for deepfake detection of frontal face videos, refAbstract=null), Reference(id=1322963020124651671, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=993, pageEnd=1000, url=null, language=null, rfNumber=null, rfOrder=74, authorNames=Shao C, Zhang F, Wang J X, Zhang B K, journalName=null, refType=null, unstructuredReference=ShaoC，ZhangF，WangJ X and ZhangB K. 2025. Sample based contrastive learning for DeepFake detection//Proceedings of the 2nd International Conference on Networks，Communications and Intelligent Computing （NCIC 2024）. Singapore，Singapore： Springer： 993-1000 ［DOI： 10.1007/978-981-96-5006-4_86］, articleTitle=Sample based contrastive learning for DeepFake detection, refAbstract=null), Reference(id=1322963020212732056, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2309.02218.pdf, language=null, rfNumber=null, rfOrder=75, authorNames=Song H, Huang S, Dong Y, Tu W, journalName=null, refType=null, unstructuredReference=SongH，HuangS，DongY and TuW. 2023. Robustness and generalizability of deepfake detection： a study with diffusion models ［EB/OL］. ［2026-01-10］., articleTitle=Robustness and generalizability of deepfake detection： a study with diffusion models, refAbstract=null), Reference(id=1322963020296618137, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2020, volume=317, issue=null, pageStart=null, pageEnd=110502, url=null, language=null, rfNumber=null, rfOrder=76, authorNames=Song J, Chen Z, Vorburger T V, Soons J A, journalName=Forensic Science International, refType=null, unstructuredReference=SongJ，ChenZ，VorburgerT V and SoonsJ A. 2020. Evaluating likelihood ratio （LR） for firearm evidence identifications in forensic science based on the congruent matching cells （CMC） method. Forensic Science International，317： #110502 ［DOI： 10.1016/j.forsciint.2020.110502］, articleTitle=Evaluating likelihood ratio （LR） for firearm evidence identifications in forensic science based on the congruent matching cells （CMC） method, refAbstract=null), Reference(id=1322963020372115610, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=647, pageEnd=657, url=null, language=null, rfNumber=null, rfOrder=77, authorNames=Stamnas S, Sanchez V, journalName=null, refType=null, unstructuredReference=StamnasS and SanchezV. 2025. DiffFake： exposing deepfakes using differential anomaly detection//Proceedings of 2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops （WACVW）. Tucson，USA： IEEE： 647-657 ［DOI： #10.1109/WACVW65960.2025.00079］, articleTitle=DiffFake： exposing deepfakes using differential anomaly detection, refAbstract=null), Reference(id=1322963020464390299, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=31, issue=5, pageStart=null, pageEnd=359, url=null, language=null, rfNumber=null, rfOrder=78, authorNames=Sun C L, Li W J, journalName=Multimedia Systems, refType=null, unstructuredReference=SunC L and LiW J. 2025. A two-stage interaction approach for enhancing generalization of deepfake detection. Multimedia Systems，31（5）： #359 ［DOI： 10.1007/s00530-025-01942-y］, articleTitle=A two-stage interaction approach for enhancing generalization of deepfake detection, refAbstract=null), Reference(id=1322963020523110556, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=133, issue=2, pageStart=628, pageEnd=651, url=null, language=null, rfNumber=null, rfOrder=79, authorNames=Sun Z M, Chen S, Yao T P, Yi R, Ding S H, Ma L Z, journalName=International Journal of Computer Vision, refType=null, unstructuredReference=SunZ M，ChenS，YaoT P，YiR，DingS H and MaL Z. 2025. Rethinking open-world DeepFake attribution with multi-perspective sensory learning. International Journal of Computer Vision，133（2）： 628-651 ［DOI： 10.1007/s11263-024-02184-7］, articleTitle=Rethinking open-world DeepFake attribution with multi-perspective sensory learning, refAbstract=null), Reference(id=1322963020602802333, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2022, volume=46, issue=null, pageStart=null, pageEnd=105716, url=null, language=null, rfNumber=null, rfOrder=80, authorNames=Van Der Sloot B and Wagensveld Y, journalName=Computer Law & Security Review, refType=null, unstructuredReference=Van Der Sloot B and Wagensveld Y. 2022. Deepfakes： regulatory challenges for the synthetic society. Computer Law & Security Review，46： #105716 ［DOI： 10.1016/j.clsr.2022.105716］, articleTitle=Deepfakes： regulatory challenges for the synthetic society, refAbstract=null), Reference(id=1322963020669911198, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=8, issue=null, pageStart=null, pageEnd=100466, url=null, language=null, rfNumber=null, rfOrder=81, authorNames=Van Lierop S, Ramos D, Sjerps M, Ypma R, journalName=Forensic Science International： Synergy, refType=null, unstructuredReference=Van LieropS，RamosD，SjerpsM and YpmaR. 2024. An overview of log likelihood ratio cost in forensic science-where is it used and what values can we expect？ Forensic Science International： Synergy，8： #100466 ［DOI： 10.1016/j.fsisyn.2024.100466］, articleTitle=An overview of log likelihood ratio cost in forensic science-where is it used and what values can we expect？, refAbstract=null), Reference(id=1322963020732825759, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2020, volume=16, issue=4, pageStart=14, pageEnd=17, url=null, language=null, rfNumber=null, rfOrder=82, authorNames=Venema A E, Geradts Z J, journalName=Scitech Lawyer, refType=null, unstructuredReference=VenemaA E and GeradtsZ J. 2020. Digital forensics，deepfakes，and the legal process. Scitech Lawyer，16（4）： 14-17，23, articleTitle=Digital forensics，deepfakes，and the legal process, refAbstract=null), Reference(id=1322963020808323232, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=32, issue=null, pageStart=896, pageEnd=900, url=null, language=null, rfNumber=null, rfOrder=83, authorNames=Wang C P, Meng L S, Xia Z Q, Ren N, Ma B, journalName=IEEE Signal Processing Letters, refType=null, unstructuredReference=WangC P，MengL S，XiaZ Q，RenN and MaB. 2025. Cross-domain deepfake detection based on latent domain knowledge distillation. IEEE Signal Processing Letters，32： 896-900 ［DOI： 10.1109/LSP.2025.3540941］, articleTitle=Cross-domain deepfake detection based on latent domain knowledge distillation, refAbstract=null), Reference(id=1322963020888015009, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=http://arxiv.org/pdf/2411.18572.pdf, language=null, rfNumber=null, rfOrder=84, authorNames=Wang H Y, Li S, He J, Qian Z X, Zhang X P, Fan S L, journalName=null, refType=null, unstructuredReference=WangH Y，LiS，HeJ，QianZ X，ZhangX P and FanS L. 2024. Exploring depth information for detecting manipulated face videos ［EB/OL］. ［2026-01-10］., articleTitle=Exploring depth information for detecting manipulated face videos, refAbstract=null), Reference(id=1322963020950929570, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=397, pageEnd=401, url=null, language=null, rfNumber=null, rfOrder=85, authorNames=Wang Y F, Liao G J, journalName=null, refType=null, unstructuredReference=WangY F and LiaoG J. 2024. Deepfake video detection based on image source anomaly//Proceedings of the 2nd IEEE International Conference on Image Processing and Computer Applications （ICIPCA）. Shenyang，China： IEEE： 397-401 ［DOI： 10.1109/ICIPCA61593.2024.10709022］, articleTitle=Deepfake video detection based on image source anomaly, refAbstract=null), Reference(id=1322963021026427043, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2023, volume=2023, issue=1, pageStart=null, pageEnd=14, url=null, language=null, rfNumber=null, rfOrder=86, authorNames=Waseem S, Abu-Bakar S A R S, Omar Z, Ahmed B A, Baloch S, Hafeezallah A, journalName=EURASIP Journal on Image and Video Processing, refType=null, unstructuredReference=WaseemS，Abu-BakarS A R S，OmarZ，AhmedB A，BalochS and HafeezallahA. 2023. Multi-attention-based approach for deepfake face and expression swap detection and localization. EURASIP Journal on Image and Video Processing，2023（1）： #14 ［DOI： 10.1186/s13640-023-00614-z］, articleTitle=Multi-attention-based approach for deepfake face and expression swap detection and localization, refAbstract=null), Reference(id=1322963021093535908, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024a, volume=5, issue=1, pageStart=93, pageEnd=106, url=null, language=null, rfNumber=null, rfOrder=87, authorNames=Xu Y, Terhörst P, Pedersen M, Raja K, journalName=IEEE Transactions on Technology and Society, refType=null, unstructuredReference=XuY，TerhörstP，PedersenM and RajaK. 2024a. Analyzing fairness in deepfake detection with massively annotated databases. IEEE Transactions on Technology and Society，5（1）： 93-106 ［DOI： 10.1109/TTS.2024.3365421］, articleTitle=Analyzing fairness in deepfake detection with massively annotated databases, refAbstract=null), Reference(id=1322963021164839077, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024b, volume=132, issue=12, pageStart=5663, pageEnd=5680, url=null, language=null, rfNumber=null, rfOrder=88, authorNames=Xu Y T, Liang J, Sheng L J, Zhang X Y, journalName=International Journal of Computer Vision, refType=null, unstructuredReference=XuY T，LiangJ，ShengL J and ZhangX Y. 2024b. Learning spatiotemporal inconsistency via thumbnail layout for face deepfake detection. International Journal of Computer Vision，132（12）： 5663-5680 ［DOI： 10.1007/s11263-024-02054-2］, articleTitle=Learning spatiotemporal inconsistency via thumbnail layout for face deepfake detection, refAbstract=null), Reference(id=1322963021227753638, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2406.13495.pdf, language=null, rfNumber=null, rfOrder=89, authorNames=Yan Z, Yao T, Chen S, Zhao Y, Fu X, Zhu J, journalName=null, refType=null, unstructuredReference=YanZ，YaoT，ChenS，ZhaoY，FuX，ZhuJ，et al. 2024. DF40： toward next-generation deepfake detection ［EB/OL］. ［2026-01-10］., articleTitle=DF40： toward next-generation deepfake detection, refAbstract=null), Reference(id=1322963021294862503, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2023, volume=9, issue=6, pageStart=1496, pageEnd=1509, url=null, language=null, rfNumber=null, rfOrder=90, authorNames=Yang J, Sun Y R, Mao M Y, Bai L Z, Zhang S Y, Wang F, journalName=IEEE Transactions on Big Data, refType=null, unstructuredReference=YangJ，SunY R，MaoM Y，BaiL Z，ZhangS Y and WangF. 2023. Model-agnostic method： exposing deepfake using pixel-wise spatial and temporal fingerprints. IEEE Transactions on Big Data，9（6）： 1496-1509 ［DOI： 10.1109/TBDATA.2023.3284272］, articleTitle=Model-agnostic method： exposing deepfake using pixel-wise spatial and temporal fingerprints, refAbstract=null), Reference(id=1322963021370359976, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2022, volume=27, issue=9, pageStart=2708, pageEnd=2720, url=null, language=null, rfNumber=null, rfOrder=91, authorNames=Yang S C, Wang J, Sun Y L, Tang J H, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=YangS C，WangJ，SunY L and TangJ H. 2022. Multi-level features global consistency for human facial deepfake detection. Journal of Image and Graphics，27（9）： 2708-2720, articleTitle=Multi-level features global consistency for human facial deepfake detection, refAbstract=null), Reference(id=1322963021466828969, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2022, volume=27, issue=9, pageStart=2708, pageEnd=2720, url=null, language=null, rfNumber=null, rfOrder=92, authorNames=杨少聪, 王健, 孙运莲, 唐金辉, journalName=中国图象图形学报, refType=null, unstructuredReference=杨少聪，王健，孙运莲，唐金辉. 2022. 多级特征全局一致性的伪造人脸检测. 中国图象图形学报，27（9）： 2708-2720 ［DOI： 10.11834/jig.211254］, articleTitle=多级特征全局一致性的伪造人脸检测, refAbstract=null), Reference(id=1322963021542326442, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=8261, pageEnd=8265, url=null, language=null, rfNumber=null, rfOrder=93, authorNames=Yang X, Li Y, Lyu S, journalName=null, refType=null, unstructuredReference=YangX，LiY and LyuS. 2019. Exposing deep fakes using inconsistent head poses//Proceedings of 2019 IEEE International Conference on Acoustics，Speech and Signal Processing （ICASSP）. Brighton，UK： IEEE： 8261-8265 ［DOI： 10.1109/ICASSP.2019.8683164］, articleTitle=Exposing deep fakes using inconsistent head poses, refAbstract=null), Reference(id=1322963021605241003, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2024, volume=20, issue=8, pageStart=null, pageEnd=253, url=null, language=null, rfNumber=null, rfOrder=94, authorNames=Yang Y Q, Joukovsky B, Mogrovejo J O, Tuytelaars T, Deligiannis N, journalName=ACM Transactions on Multimedia Computing，Communications and Applications, refType=null, unstructuredReference=YangY Q，JoukovskyB，MogrovejoJ O，TuytelaarsT and DeligiannisN. 2024. SNIPPET： a framework for subjective evaluation of visual explanations applied to DeepFake detection. ACM Transactions on Multimedia Computing，Communications and Applications，20（8）： #253 ［DOI： 10.1145/3665248］, articleTitle=SNIPPET： a framework for subjective evaluation of visual explanations applied to DeepFake detection, refAbstract=null), Reference(id=1322963021680738476, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=30, issue=7, pageStart=2343, pageEnd=2363, url=null, language=null, rfNumber=null, rfOrder=95, authorNames=Yao W D, Li P C, Zhao Y, Wu H C, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=YaoW D，LiP C，ZhaoY and WuH C. 2025. Review of research on face deepfake detection methods. Journal of Image and Graphics，30（7）： 2343-2363, articleTitle=Review of research on face deepfake detection methods, refAbstract=null), Reference(id=1322963021768818861, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=30, issue=7, pageStart=2343, pageEnd=2363, url=null, language=null, rfNumber=null, rfOrder=96, authorNames=姚文达, 李盼池, 赵娅, 吴洪超, journalName=中国图象图形学报, refType=null, unstructuredReference=姚文达，李盼池，赵娅，吴洪超. 2025. 人脸深度伪造检测方法研究综述. 中国图象图形学报，30（7）： 2343-2363 ［DOI： 10.11834/jig.240586］, articleTitle=人脸深度伪造检测方法研究综述, refAbstract=null), Reference(id=1322963021823344814, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=null, rfOrder=97, authorNames=Zeng S D, Yi J Y, Tao J H, He J Y, Lian Z, Liang S, journalName=null, refType=null, unstructuredReference=ZengS D，YiJ Y，TaoJ H，HeJ Y，LianZ，LiangS，et al. 2025. Adversarial training and gradient optimization for partially deepfake audio localization//Proceedings of 2025 IEEE International Conference on Acoustics，Speech and Signal Processing （ICASSP）. Hyderabad，India： IEEE： 1-5 ［DOI： 10.1109/ICASSP49660.2025.10890470］, articleTitle=Adversarial training and gradient optimization for partially deepfake audio localization, refAbstract=null), Reference(id=1322963021890453679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025a, volume=22, issue=2, pageStart=1796, pageEnd=1809, url=null, language=null, rfNumber=null, rfOrder=98, authorNames=Zhang B L, Yin Q L, Lu W, Luo X Y, journalName=IEEE Transactions on Dependable and Secure Computing, refType=null, unstructuredReference=ZhangB L，YinQ L，LuW and LuoX Y. 2025a. Deepfake detection and localization using multi-view inconsistency measurement. IEEE Transactions on Dependable and Secure Computing，22（2）： 1796-1809 ［DOI： 10.1109/TDSC.2024.3472064］, articleTitle=Deepfake detection and localization using multi-view inconsistency measurement, refAbstract=null), Reference(id=1322963021965951152, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=#238, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=99, authorNames=Zhang C H, journalName=null, refType=null, unstructuredReference=ZhangC H. 2025. Federated learning-based cross-domain face forgery detection for consumer IOT systems//Proceedings of the 4th International Conference on Electronic Information Engineering and Data Processing（Mohd Zain A B，Chen L，eds.） （EIEDP 2025. Kuala Lumpur，Malaysia： SPIE： #238 ［DOI： 10.1117/12.3067515］, articleTitle=Federated learning-based cross-domain face forgery detection for consumer IOT systems, refAbstract=null), Reference(id=1322963022049837233, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025b, volume=47, issue=12, pageStart=12021, pageEnd=12037, url=null, language=null, rfNumber=null, rfOrder=100, authorNames=Zhang Z Y, Zhang J, Zhou W B, Zhou X H, Guo Q, Zhang W M, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=ZhangZ Y，ZhangJ，ZhouW B，ZhouX H，GuoQ，ZhangW M，et al. 2025b. FaceTracer： unveiling source identities from swapped face images and videos for fraud prevention. IEEE Transactions on Pattern Analysis and Machine Intelligence，47（12）： 12021-12037 ［DOI： 10.1109/TPAMI.2025.3601141］, articleTitle=FaceTracer： unveiling source identities from swapped face images and videos for fraud prevention, refAbstract=null), Reference(id=1322963022116946098, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=101, authorNames=Zhou C Z, Zhang D, Chen Z, Zhao J Q, Zhang G B, Wei C, journalName=medium and device based on cross-modal learning, refType=null, unstructuredReference=ZhouC Z，ZhangD，ChenZ，ZhaoJ Q，ZhangG B and WeiC. 2025. A speaking face deepfake detection method，medium and device based on cross-modal learning： #CN120126223［P］. 2025, articleTitle=null, refAbstract=null), Reference(id=1322963022179860659, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=102, authorNames=Zi B J, Chang M H, Chen J J, Ma X J, Jiang Y G, journalName=［s.n.］, refType=null, unstructuredReference=ZiB J，ChangM H，ChenJ J，MaX J and JiangY G. 2020. WildDeepfake： a challenging real-world dataset for deepfake detection//Proceedings of the 28th ACM International Conference on Multimedia： ［s.l.］： ［s.n.］, articleTitle=WildDeepfake： a challenging real-world dataset for deepfake detection, refAbstract=null)], funds=[Fund(id=1322963009118797896, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, awardId=null, language=EN, fundingSource=Major Project of the National Social Science Fund of China （25&ZD238）；Graduate Research Project of People’s Public Security University of China （2024yjsky032）, fundOrder=null, country=null), Fund(id=1322963009198489673, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, awardId=null, language=CN, fundingSource=国家社会科学基金重大项目（25&ZD238）；中国人民公安大学研究生科研项目（2024yjsky032）, fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322963002869284869, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, xref=null, ext=[AuthorCompanyExt(id=1322963002877673478, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, companyId=1322963002869284869, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Criminal Investigation，People’s Public Security University of China，Beijing 100038，China), AuthorCompanyExt(id=1322963002886062087, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, companyId=1322963002869284869, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国人民公安大学侦查学院，北京 100038)])], figs=[ArticleFig(id=1322963004580560931, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.1, caption=Fishbone diagram of the temporal development of the dataset, figureFileSmall=ujCRL3JuitptpRF5Nh1DBw==, figureFileBig=UrxVyc+y98j5tjA3SWUfPw==, tableContent=null), ArticleFig(id=1322963004672835620, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图1, caption=数据集时间发展的鱼骨图, figureFileSmall=ujCRL3JuitptpRF5Nh1DBw==, figureFileBig=UrxVyc+y98j5tjA3SWUfPw==, tableContent=null), ArticleFig(id=1322963004874162213, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.2, caption=Key information extracted from facial images, figureFileSmall=Sg5NcDtdTitwVNPbAyX4aw==, figureFileBig=aRkXqGQEFosjXM0x/KJLPQ==, tableContent=null), ArticleFig(id=1322963004941271078, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图2, caption=从人脸图像中提取的关键信息, figureFileSmall=Sg5NcDtdTitwVNPbAyX4aw==, figureFileBig=aRkXqGQEFosjXM0x/KJLPQ==, tableContent=null), ArticleFig(id=1322963005008379943, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.3, caption=Deepfake image generation process, figureFileSmall=aoz0O146mlj1ucwrRSlpIg==, figureFileBig=o52SwPhEcCwXg8StJ/DOgg==, tableContent=null), ArticleFig(id=1322963006690295848, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图3, caption=生成深度伪造人脸图像的流程, figureFileSmall=aoz0O146mlj1ucwrRSlpIg==, figureFileBig=o52SwPhEcCwXg8StJ/DOgg==, tableContent=null), ArticleFig(id=1322963006757404713, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.4, caption=Schematic of GAN-based forged facial image generation, figureFileSmall=E/OQ1/H6Zt/uo5xmE4bJtw==, figureFileBig=GKYr/dMgABnLz/39HDVODg==, tableContent=null), ArticleFig(id=1322963006845485098, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图4, caption=基于生成对抗网络的伪造人脸图像生成机制示意图, figureFileSmall=E/OQ1/H6Zt/uo5xmE4bJtw==, figureFileBig=GKYr/dMgABnLz/39HDVODg==, tableContent=null), ArticleFig(id=1322963006925176875, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.5, caption=Schematic of autoencoder-based forged facial image generation, figureFileSmall=yT8jsQYsNO4ZM9FFtZErrg==, figureFileBig=it+GHV9wvjy2WZ7x4BHnEA==, tableContent=null), ArticleFig(id=1322963007009062956, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图5, caption=基于自编码器的伪造人脸图像生成机制示意图, figureFileSmall=yT8jsQYsNO4ZM9FFtZErrg==, figureFileBig=it+GHV9wvjy2WZ7x4BHnEA==, tableContent=null), ArticleFig(id=1322963007067783213, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.6, caption=Schematic of diffusion-based forged facial image generation, figureFileSmall=CI7Izg1mLgBaQAVYlCBVmw==, figureFileBig=4bHXMtK0shalcyS+Ix1A0Q==, tableContent=null), ArticleFig(id=1322963007160057902, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图6, caption=基于扩散模型的伪造人脸图像生成机制示意图, figureFileSmall=CI7Izg1mLgBaQAVYlCBVmw==, figureFileBig=4bHXMtK0shalcyS+Ix1A0Q==, tableContent=null), ArticleFig(id=1322963007248138287, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.7, caption=The number of published papers on deepfake face image detection in the past five years, figureFileSmall=6AWYKpjt08Vrrtk4wYXjYw==, figureFileBig=s9hS3wB/++YFiAvFoAde9g==, tableContent=null), ArticleFig(id=1322963007327830064, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图7, caption=深度伪造人脸图像检测文献近5年发表数量, figureFileSmall=6AWYKpjt08Vrrtk4wYXjYw==, figureFileBig=s9hS3wB/++YFiAvFoAde9g==, tableContent=null), ArticleFig(id=1322963007399133233, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.8, caption=Keyword co-occurrence visualization using VOSviewer, figureFileSmall=b7CAcmDDUc5gBKxoJG57Kg==, figureFileBig=4P+216Svz6qRi9ZnP4b6pA==, tableContent=null), ArticleFig(id=1322963007474630706, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图8, caption=使用VOSviewer的关键词共现可视化, figureFileSmall=b7CAcmDDUc5gBKxoJG57Kg==, figureFileBig=4P+216Svz6qRi9ZnP4b6pA==, tableContent=null), ArticleFig(id=1322963007550128179, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.9, caption=Classification of deepfake detection methods based on technical principles, figureFileSmall=JlQWqPLS6mRY62Uf4Pj5iQ==, figureFileBig=J++AOhieK9clxxKNjOvRyQ==, tableContent=null), ArticleFig(id=1322963007621431348, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图9, caption=按技术原理对深度伪造人脸检测方法的分类, figureFileSmall=JlQWqPLS6mRY62Uf4Pj5iQ==, figureFileBig=J++AOhieK9clxxKNjOvRyQ==, tableContent=null), ArticleFig(id=1322963007696928821, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.10, caption=Classification of deepfake detection methods by application stage, figureFileSmall=hboXO6bWp1lygvnMtAmx5A==, figureFileBig=PKedcytJEsKgqfg/YTX0/Q==, tableContent=null), ArticleFig(id=1322963007785009206, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图10, caption=按应用阶段对深度伪造人脸检测方法的分类, figureFileSmall=hboXO6bWp1lygvnMtAmx5A==, figureFileBig=PKedcytJEsKgqfg/YTX0/Q==, tableContent=null), ArticleFig(id=1322963007856312375, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.11, caption=Premises for the authentication of deepfake facial images, figureFileSmall=TYeJmhaZx7vTzbBZrh17yA==, figureFileBig=qTWDMz5yDLg4+ImTKIlbaA==, tableContent=null), ArticleFig(id=1322963007919226936, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图11, caption=深度伪造人脸图像的鉴定前提, figureFileSmall=TYeJmhaZx7vTzbBZrh17yA==, figureFileBig=qTWDMz5yDLg4+ImTKIlbaA==, tableContent=null), ArticleFig(id=1322963007998918713, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Fig.12, caption=Relationship between detection and identification, figureFileSmall=hOKux8OBqpWQChKGK2T0gg==, figureFileBig=ij45YnJB3SArIZK/QoBH1w==, tableContent=null), ArticleFig(id=1322963008061833274, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=CN, label=图12, caption=检测与鉴定的关系, figureFileSmall=hOKux8OBqpWQChKGK2T0gg==, figureFileBig=ij45YnJB3SArIZK/QoBH1w==, tableContent=null), ArticleFig(id=1322963008124747835, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322962994438734827, language=EN, label=Table 1, caption=Representative datasets of deepfake faces from 2018 to 2024, figureFileSmall=null, figureFileBig=null, tableContent=
Advances in forensic science of deepfake facial images evidence
Tianli Guo, Jisong Li, Yunqi Tang*
Affiliations
School of Criminal Investigation，People’s Public Security University of China，Beijing 100038，China
出版时间: 2026-10-16
doi: 10.11834/jig.250610
文章导航
摘要
收起
随着生成对抗网络（generative adversarial network，GAN）、自编码器（autoencoder，AE）和扩散模型（diffusion model，DM）等深度伪造技术的快速发展，深度伪造人脸图像广泛用于制作非自愿色情内容、实施电信诈骗及传播政治虚假信息等恶意行为。作为新型数字证据，深度伪造不仅频繁出现在当前犯罪活动中，还可能被用于虚假指控或操控监控记录，严重削弱法庭证据科学中人脸图像分析的可靠性，进而威胁刑事司法的公正性。本文系统梳理了关键数据集的发展脉络与深度伪造人脸图像的技术演进路径，深入剖析其生成机制的核心架构，涵盖主要技术路线、理论基础与功能逻辑；基于Web of Science数据库筛选出的737篇文献，采用VOSviewer进行文献计量分析，识别该领域的研究趋势，并揭示现有检测技术研究与司法实践中证据鉴伪实际需求之间的显著脱节。本研究提出将深度伪造人脸图像检测方法划分为技术原理导向与应用阶段适配两类互补框架，以应对不同阶段的证据鉴定需求。针对深度伪造人脸图像作为新型犯罪载体所带来的证据可信性挑战，本文主张法庭证据鉴定人应推动检测向鉴定的转化，实现检测结果与贝叶斯推理框架的融合，提升其在司法证明中的可采性与说服力。本研究衔接计算机视觉技术发展与法庭证据实践需求，明确了从技术检测到司法鉴定的逻辑路径，为法庭科学研究人员与司法实务工作者提供了具有技术价值的理论参考。
关键词
司法
/
证据
/
人脸图像
/
深度伪造
/
检测
/
鉴定
Abstract
收起
With the rapid advancement of deepfake technologies，including generative adversarial networks （GANs），autoencoders （AEs），and diffusion models （DMs），deepfake facial images have been increasingly exploited for malicious purposes，such as the creation of nonconsensual pornographic content，telecommunication fraud，and the propagation of political disinformation. In recent years，the continuous iteration of these core deepfake technologies has considerably lowered the technical threshold for generating high-fidelity fake facial images： GANs，with their adversarial training mechanism between generators and discriminators，enable the rapid synthesis of realistic facial features； AEs，relying on unsupervised learning and feature reconstruction capabilities，excel in simulating subtle facial expressions and skin textures； diffusion models，through step-by-step noise reduction and feature enhancement，have further broken through the limitations of traditional deepfake technologies in terms of image clarity and detail authenticity，making deepfake facial images increasingly difficult to distinguish with the naked eye and even challenging preliminary manual identification in forensic investigations. As an emerging form of digital evidence，deepfakes not only pervade contemporary criminal activities but also risk being weaponized for false accusations or the tampering of surveillance records，thereby severely undermining the reliability of facial image analysis in forensic science and threatening the integrity of the criminal justice system. To address the aforementioned challenges，this study systematically traces the developmental trajectory of key datasets and the technological evolution of deepfake facial images while conducting an in-depth dissection of the core architecture underlying their generation mechanisms，encompassing primary technical routes，theoretical underpinnings，and functional logics. In terms of dataset development，the evolution process from early small-scale，single-scene datasets （such as CelebA and LFW） to large-scale，multiscenario，high-diversity datasets （such as DFDC，FF++，and Celeb-DF） is sorted out，with the advantages and limitations of each type of dataset analyzed in terms of sample size，fake generation technology coverage，and scene diversity Moreover，the lack of standardized，forensic-oriented datasets has become one of the key bottlenecks restricting the practical application of deepfake detection technologies. In terms of technological evolution，the development of deepfake facial image technology is divided into three stages： the initial exploration stage dominated by GANs，the improvement stage supplemented by AEs，and the mature stage driven by diffusion models. The theoretical breakthroughs and technical improvements of each stage are elaborated，and the internal logic of the continuous improvement of fake image fidelity and the continuous reduction of generation costs is revealed. In the in-depth analysis of generation mechanisms，the core principles of the three mainstream technologies are focused on，the differences in their technical routes and functional characteristics are clarified，and the common key links and potential vulnerabilities in the generation process are summarized，laying a theoretical foundation for the subsequent design of targeted detection and identification methods. On the basis of 737 relevant articles retrieved and screened from the Web of Science database，a bibliometric analysis is performed via VOSviewer to identify research trends in the field and illuminate the substantial disconnect between existing detection technology research and the practical requirements for evidence authentication in judicial practice. The retrieval and screening process strictly followed the PRISMA guidelines： “deepfake”，“facial image”，“forensic science”，“identification”，and “detection” are adopted as key search terms； the retrieval time range is defined from the emergence of deepfake technology to the present； and irrelevant literature，review papers with low innovation，and duplicate publications are excluded through preliminary screening and full-text reading. The bibliometric analysis focuses on three core dimensions： research hotspots，institutional cooperation，and research frontiers. Results show that current research in the field is mainly concentrated on the optimization of detection algorithms （such as deep learning-based feature extraction and classification models），while research on the translation of detection results into forensic authentication，the formulation of forensic identification standards，and the adaptation of detection technologies to judicial practice scenarios is relatively scarce. This disconnect is mainly reflected in two aspects： on the one hand，most existing detection technologies focus on technical accuracy，ignoring the admissibility requirements of judicial evidence （such as objectivity，authenticity，and relevance）； on the other hand，forensic examiners lack effective methods to integrate technical detection results into judicial authentication，leading to the situation where advanced detection technologies fail to be effectively applied in judicial practice. In response to the identified research-practice disconnect，this study proposes a classification of deepfake facial image detection methods into two complementary frameworks： technology principle oriented and application scenario adaptive，designed to address evidence authentication needs across distinct stages. The technology-principle-oriented framework takes the technical principles of deepfake generation as the core，classifies detection methods in accordance with the technical characteristics of different generation technologies （such as GAN-based detection，AE-based detection，and diffusion model-based detection），and focuses on improving the accuracy and generalization ability of detection，thus being mainly applicable to the preliminary technical screening stage of evidence in forensic investigations. The application-scenario-adaptive framework takes the actual needs of different judicial stages （such as investigation，prosecution，and trial） as guidance，classifies detection methods in light of the scenario characteristics and evidence requirements of each stage，and focuses on enhancing the adaptability and operability of detection methods，thereby being mainly applicable to the formal evidence authentication stage in judicial practice. The two frameworks are complementary and mutually supportive： the technology-principle-oriented framework provides technical support for the application-scenario-adaptive framework，and the application-scenario-adaptive framework guides the direction of technical optimization，thus forming a complete detection system covering the entire process of forensic evidence authentication. In response to the evidentiary credibility challenges posed by deepfake facial images as a novel criminal vector，this study argues that forensic examiners should facilitate the translation of detection outcomes into forensic authentication，integrating detection results with the Bayesian inference framework to enhance their admissibility and probative force in judicial proceedings. Specifically，a Bayesian inference-based forensic authentication model is proposed. Technical detection results are taken as the prior probability，forensic examiners’ professional experience and case context are integrated to determine the likelihood ratio，and the posterior probability of the authenticity of facial images is ultimately calculated via the Bayesian formula to convert objective technical indicators into credible judicial authentication conclusions. Furthermore，forensic examiners should continuously improve their understanding of deepfake technologies，master the working principles and limitations of detection technologies，and avoid over-reliance on technical detection results to ensure the scientificity and rigor of forensic authentication. In conclusion，by bridging the advancements in computer vision technology with the practical demands of forensic evidence practice，this research articulates the logical pathway from technical detection to judicial authentication，providing a theoretically insightful and practically relevant reference for forensic science researchers and judicial practitioners alike. For forensic science researchers，this study clarifies the research direction of integrating technical research with judicial practice，identifies the key issues to be addressed in the future （such as the construction of forensic-oriented datasets，the optimization of detection algorithms adapted to judicial scenarios，and the formulation of forensic identification standards），and offers a theoretical framework for subsequent research. For judicial practitioners，this study provides a practical operational path for the forensic authentication of deepfake facial images，facilitates the better grasp of the application methods and precautions of deepfake detection technologies，and elevates the efficiency and accuracy of digital evidence authentication. Additionally，this study offers a reference for the formulation of relevant laws and regulations，which helps improve the legal system of digital evidence authentication and promote the sound development of the criminal justice system in the era of deepfake technology.
尽管不同类型信息的具体表示与特征提取方法较为复杂，但图2中的各子图仍能直观反映不同模态的基本分布与结构。其中，语义掩码通过像素级标注实现结构化面部分割，明确眼、鼻和口等关键面部部位的边缘轮廓与边界，完成空间定位与语义区分；颜色与深度信息互补，颜色通道反映表面外观（如色彩分布与纹理），深度数据则通过空间距离刻画 3D 面部几何特征（如鼻梁凸起、下颌凹陷），二者共同提供多模态的面部外观描述；在频域分析中，高频成分体现皮肤纹理、睫毛等细节，中频成分连接局部结构与整体形态，低频成分主导全局轮廓与宏观布局（如脸型、五官排列），反映粗粒度结构特征；空域特征则随维度变化而呈现不同表征能力。在二维空间中，像素梯度与密度可以刻画局部复杂性，例如眼部区域因纹理更为丰富而表现出更剧烈的梯度变化；在三维空间中，不同坐标轴用于捕捉特定几何属性，z轴聚焦于深度方向的形变，x/y轴描述平面内的轮廓与纹理，从而形成多视角的空间表达。
本研究以“（“deepfake” OR “face forgery” OR “face manipulation” OR “face swap” OR “facial deepfake”） AND （“face” OR “facial”）”为主题，在Web of Science核心合集（core collection）检索近5年文献，共获取845篇文档；经筛选排除与深度伪造人脸不相关的内容及综述类文章后，剩余737篇有效文献。保留文献的题目与摘要信息并导入VOSviewer，以Binary Counting方式计算关键词频数，选取频数大于20的关键词共196个，展示前60%（共118个）；将标签最大长度设置为10、线长设置为1 000，最终生成网络可视化图谱。
Forensics analysis of WI-FI communication traces in mobile devices
AmundsenA E and OvensK M. 2017. Forensics analysis of WI-FI communication traces in mobile devices//Proceedings of 2017 IEEE International Conference on Big Data （Big Data）. Boston，USA： IEEE： 3632-3637 ［DOI： 10.1109/BigData.2017.8258357］
Unmasking deepfakes： a systematic review of deepfake detection and generation techniques using artificial intelligence
AbbasF and TaeihaghA. 2024. Unmasking deepfakes： a systematic review of deepfake detection and generation techniques using artificial intelligence. Expert Systems with Applications，252： #124260 ［DOI： 10.1016/j.eswa.2024.124260］
A comparison of likelihood ratios calculated from surface DNA mixtures using MPS and CE technologies
AgudoM M，FantinatoC，RosethA，AanesH，GillP，FonneløpA E，et al. 2024. A comparison of likelihood ratios calculated from surface DNA mixtures using MPS and CE technologies. Forensic Science International： Genetics，73： #103111 ［DOI： 10.1016/j.fsigen.2024.103111］
The U.S. cyber threat landscape
AlhajjarE and LeeK. 2022. The U.S. cyber threat landscape. European Conference on Cyber Warfare and Security，21（1）： 18-24 ［DOI： 10.34190/eccws.21.1.197］
Deepfakes detection techniques using deep learning： a survey
AlmarsA M. 2021. Deepfakes detection techniques using deep learning： a survey. Journal of Computer and Communications，9（5）： 20-35 ［DOI： 10.4236/jcc.2021.95003］
DFFMD： a deepfake face mask dataset for infectious disease era with deepfake detection algorithms
AlnaimN M，AlmutairiZ M，AlsuwatM S，AlalawiH H，AlshobailiA and AleneziF S. 2023. DFFMD： a deepfake face mask dataset for infectious disease era with deepfake detection algorithms. IEEE Access，11： 16711-16722 ［DOI： 10.1109/ACCESS.2023.3246661］
Explainable deepfake detection： a multi-model framework with human-interpretable rationales for legal investigation purposes
BharatiN，WongP，MostéfaouiS K，KbaierD and CollieJ. 2026. Explainable deepfake detection： a multi-model framework with human-interpretable rationales for legal investigation purposes. Machine Learning with Applications，23： #100819 ［DOI： 10.1016/j.mlwa.2025.100819］
Testing human ability to detect “deepfake” images of human faces
BrayS D，JohnsonS D and KleinbergB. 2023. Testing human ability to detect “deepfake” images of human faces. Journal of Cyber Security，9（1） ［DOI： 10.1093/cybsec/tyad011］
A scoping study： crime and connected and autonomous vehicles
BrownA，JohnsonS D and TuptukN. 2025. A scoping study： crime and connected and autonomous vehicles. Crime Science，14（1）： #2 ［DOI： 10.1186/s40163-025-00245-x］
Deepfake video detection： a novel approach via NLP-based classification
BunluesakdikulP，MahananW，SungunnasilP and SangamuangS. 2025. Deepfake video detection： a novel approach via NLP-based classification. International Journal of Computational Intelligence and Applications，24（2）： #2550001 ［DOI： 10.1142/S1469026825500014］
2022
CaiZ，StefanovK，DhallA and HayatM. 2022. Do you really mean that？ Content driven audio-visual deepfake dataset and multimodal method for temporal forgery localization//Proceedings of 2022 International Conference on Digital Image Computing： Techniques and Applications （DICTA）： 1-10 ［DOI： 10.1109/DICTA56598.2022.10034605］
Deepfake satellite imagery detection with multi-attention and super resolution
Çiftçi U A and Demirİ. 2023. Deepfake satellite imagery detection with multi-attention and super resolution//2023 IEEE International Geoscience and Remote Sensing Symposium （IGARSS）. Pasadena，USA： IEEE： 4871-4874 ［DOI： 10.1109/IGARSS52108.2023.10282927］
Div-Df： a diverse manipulation deepfake video dataset
DagarD and VishwakarmaD K. 2023. Div-Df： a diverse manipulation deepfake video dataset//Proceedings of 2023 Global Conference on Information Technologies and Communications （GCITC）. Bangalore，India： IEEE： 1-6 ［DOI： 10.1109/GCITC60406.2023.10426446］
Deepfake video detection
Dayal S B and van Niekerk B. 2021. Deepfake video detection//Proceedings of the 20th European Conference on Cyber Warfare and Security. 2021 ［DOI： 10.34190/ECCWS.21.110］
A multi-label classification method combined with texture enhancement for deepfake face detection
DengL W，WuB D and WangJ D. 2025. A multi-label classification method combined with texture enhancement for deepfake face detection. Multimedia Systems，31（6）： #410 ［DOI： 10.1007/s00530-025-01996-y］
Biometric recognition
DengW，FengJ，HuangD，KanM，SunZ，ZhengF，et al. 2022. Biometric recognition//Proceedings of the 16th Chinese Conference on Biometrics Recognition（CCBR）. Beijing，China： ［s.n.］ ［DOI： 10.1007/978-3-031-20233-9］
A survey of Deepfake and related digital forensics
DingF，KuangR S，ZhouY，SunL，ZhuX G and ZhuG P. 2024. A survey of Deepfake and related digital forensics. Journal of Image and Graphics，29（2）： 295-317
Restricted black-box adversarial attack against DeepFake face swapping
DongJ H，WangY，LaiJ H and XieX H. 2023. Restricted black-box adversarial attack against DeepFake face swapping. IEEE Transactions on Information Forensics and Security，18： 2596-2608 ［DOI： 10.1109/TIFS.2023.3266702］
Seven technologies to watch in 2024
EisensteinM. 2024. Seven technologies to watch in 2024. Nature，625（7996）： 844-848 ［DOI： 10.1038/d41586-024-00173-x］
2D-malafide： adversarial attacks against face deepfake detection systems
GaldiC，PanarielloM，TodiscoM and EvansN. 2024. 2D-malafide： adversarial attacks against face deepfake detection systems//Proceedings of 2024 International Conference of the Biometrics Special Interest Group （BIOSIG）. Darmstadt，Germany： IEEE： 1-7 ［DOI： 10.1109/BIOSIG61931.2024.10786754］
Unmasking deepfakes： a review of current datasets，tools，and detection features
GargD and GillR. 2025. Unmasking deepfakes： a review of current datasets，tools，and detection features//Proceedings of the 6th International Conference on Futuristic Trends in Networks and Computing Technologies （FTNCT06），Held in Uttarakhand，India，259： 1737-1748 ［DOI： 10.1016/j.procs.2025.04.129］
FSD-GAN： generative adversarial training for face swap detection via the latent noise fingerprint
GeJ W，CaoJ X，ZhaoZ X and LiuB. 2025. FSD-GAN： generative adversarial training for face swap detection via the latent noise fingerprint. Journal of Computer Science and Technology，40（2）： 397-412［DOI： 10.1007/s11390-024-3337-8］
ST-SBV： spatial-temporal self-blended videos for deepfake detection
GuanW N，WangW，PengB，DongJ and TanT N. 2025. ST-SBV： spatial-temporal self-blended videos for deepfake detection//Proceedings of the 7th Chinese Conference on Pattern Recognition and Computer Vision. Urumqi，China： Springer： 274-288 ［DOI： 10.1007/978-981-97-8620-6_19］
ForgeryNet： a versatile benchmark for comprehensive forgery analysis
HeY，GanB，ChenS，ZhouY，YinG，SongL，et al. 2021. ForgeryNet： a versatile benchmark for comprehensive forgery analysis//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Nashville，TN，USA： IEEE： 4358-4367 ［DOI： 10.1109/CVPR46437.2021.00434］
Learning meta model for strong generalization deepfake detection
HuangD Z and ZhangY Q. 2024. Learning meta model for strong generalization deepfake detection//Proceedings of 2024 International Joint Conference on Neural Networks. Yokohama，Japan： IEEE： 1-8 ［DOI： 10.1109/IJCNN60899.2024.10651482］
Digital forensic evidence—the missing link in threat modeling
IqbalA，OlegårdJ and GhimireR. 2020. Digital forensic evidence—the missing link in threat modeling//Proceedings of 2020 International Conference on Data Analytics for Business and Industry： Way Towards a Sustainable Economy （ICDABI）. Sakheer，Bahrain： IEEE： 1-5 ［DOI： 10.1109/ICDABI51230.2020.9325650］
Flexible multi-modality deepfake identification with dynamic learning and cross-modality inconsistency
JoelE J，KumarK P，SilarM M and RohanJ. 2025. Flexible multi-modality deepfake identification with dynamic learning and cross-modality inconsistency//Proceedings of the 3rd International Conference on Advancements in Electrical，Electronics，Communication，Computing and Automation （ICAECA 2025）. Coimbatore，India： IEEE： 1-6 ［DOI： 10.1109/ICAECA63854.2025.11012276］
#MeToo in an AI-generated deepfake sexual violence era in South Korea
JiS. 2025. #MeToo in an AI-generated deepfake sexual violence era in South Korea. Women’s Studies International Forum，112： #103146 ［DOI： 10.1016/j.wsif.2025.103146］
Model attribution of face-swap deepfake videos
JiaS，LiX and LyuS. 2022. Model attribution of face-swap deepfake videos//Proceedings of the 29th IEEE International Conference on Image Processing （ICIP）. Bordeaux，France： IEEE Computer Society： 2356-2360 ［DOI： 10.1109/ICIP46576.2022.9897972］
DeeperForensics-1.0： a large-scale dataset for real-world face forgery detection
JiangL，LiR，WuW，QianC and LoyC C. 2020. DeeperForensics-1.0： a large-scale dataset for real-world face forgery detection//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle，USA： IEEE： 2886-2895 ［DOI： 10.1109/CVPR42600.2020.00296］
A dual descriptor combined with frequency domain reconstruction learning for face forgery detection in deepfake videos
JinX，WuN，JiangQ，KouY R，DuanH X，WangP M，et al. 2024. A dual descriptor combined with frequency domain reconstruction learning for face forgery detection in deepfake videos. Forensic Science International： Digital Investigation，49： #301747 ［DOI： 10.1016/j.fsidi.2024.301747］
Countering spoof： towards detecting deepfake with multidimensional biological signals
JinX L，YeD P and ChenC X. 2021. Countering spoof： towards detecting deepfake with multidimensional biological signals. Security and Communication Networks，2021（1）： #6626974 ［DOI： 10.1155/2021/6626974］
Improving fairness in deepfake detection
JuY，HuS，JiaS，ChenG H and LyuS W. 2024. Improving fairness in deepfake detection//Proceedings of 2024 IEEE/CVF Winter Conference on Applications of Computer Vision （WACV）. Waikoloa，USA： IEEE： 4643-4653 ［DOI： 10.1109/WACV57701.2024.00459］
Progressive growing of GANs for improved quality
KarrasT，AilaT，LaineS and LehtinenJ. 2018. Progressive growing of GANs for improved quality，stability，and variation//Proceedings of the 6th International Conference on Learning Representations （ICLR）. Vancouver， Canada： ICLR
A style-based generator architecture for generative adversarial networks
KarrasT，LaineS and AilaT. 2019. A style-based generator architecture for generative adversarial networks//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Beach，USA： IEEE： 4396-4405 ［DOI： 10.1109/CVPR.2019.00453］
Role of artificial intelligence in the crime prediction and pattern analysis studies published over the last decade： a scientometric analysis
KaurM and SainiM. 2024. Role of artificial intelligence in the crime prediction and pattern analysis studies published over the last decade： a scientometric analysis. Artificial Intelligence Review，57（8）： #202 ［DOI： 10.1007/s10462-024-10823-1］
FakeAVCeleb： a novel audio-video multimodal deepfake dataset
KhalidH，TariqS，KimM and WooS S. 2021. FakeAVCeleb： a novel audio-video multimodal deepfake dataset ［EB/OL］. ［2026-01-10］.
https://arxiv.org/pdf/2108.05080.pdf
Smartphone-based deepfake detection through transfer learning and lightweight knowledge distillation technique
KhanS S，HossainR，BishalS H and KhanR. 2024. Smartphone-based deepfake detection through transfer learning and lightweight knowledge distillation technique//Proceedings of the 27th International Conference on Computer and Information Technology （ICCIT）. Cox’s Bazar，Bangladesh： IEEE： 675-680 ［DOI： 10.1109/ICCIT64611.2024.11022522］
Fake face detection methods： can they Be generalized?
KhodabakhshA，RamachandraR，RajaK，WasnikP and BuschC. 2018. Fake face detection methods： can they Be generalized?//Proceedings of 2018 International Conference of the Biometrics Special Interest Group （BIOSIG）. Darmstadt，Germany： IEEE： 1-6 ［DOI： 10.23919/BIOSIG.2018.8553251］
DeepFakes： a new threat to face recognition？
KorshunovP and MarcelS. 2018. DeepFakes： a new threat to face recognition？ Assessment and detection ［EB/OL］. ［2026-01-10］.
https://arxiv.org/pdf/1812.08685.pdf
VCF： a real-world video conference deepfake benchmark for face-swap detection and robustness evaluation
KrasilnikovM，NikitinM and KonushinA. 2025. VCF： a real-world video conference deepfake benchmark for face-swap detection and robustness evaluation. The International Archives of the Photogrammetry，Remote Sensing and Spatial Information Sciences，XLVIII-2/W9-2025： 169-174 ［DOI： 10.5194/isprs-archives-XLVIII-2-W9-2025-169-2025］
Rising threats of AI-driven child sexual abuse material
KrishnaS，DubrosaF and MilanaikR. 2024. Rising threats of AI-driven child sexual abuse material. Pediatrics，153（2）： #2023063954 ［DOI： 10.1542/peds.2023-063954］
KoDF： a large-scale Korean DeepFake detection dataset
KwonP，YouJ，NamG，ParkS and ChaeG. 2021. KoDF： a large-scale Korean DeepFake detection dataset//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision （ICCV）. Montreal，QC，Canada： IEEE： 10724-10733 ［DOI： 10.1109/ICCV48922.2021.01057］
OpenForensics： large-scale challenging dataset for multi-face forgery detection and segmentation In-the-wild
LeT N，NguyenH H，YamagishiJ and EchizenI. 2021. OpenForensics： large-scale challenging dataset for multi-face forgery detection and segmentation In-the-wild ［EB/OL］. ［2026-01-10］.
https://arxiv.org/pdf/2107.14480.pdf
Deepfake face detection and adversarial attack defense method based on multi-feature decision fusion
LeiS Z，SongJ F，FengF Y，YanZ Y and WangA X. 2025. Deepfake face detection and adversarial attack defense method based on multi-feature decision fusion. Applied Sciences，15（12）： #6588 ［DOI： 10.3390/app15126588］
Fingerprint analysis and reporting in legal trials： a critical re-evaluation
LevanonL and TullyG. 2025. Fingerprint analysis and reporting in legal trials： a critical re-evaluation. Criminal Law Forum，36（1）： 1-32 ［DOI： 10.1007/s10609-025-09497-3］
FastFace： a real-time robust algorithm for face detection
LiQ Y，JiQ G and HongS D. 2019. FastFace： a real-time robust algorithm for face detection. Journal of Image and Graphics，24（10）： 1761-1771
Celeb-DF： a large-scale challenging dataset for DeepFake forensics
LiY，YangX，SunP，QiH and LyuS. 2020. Celeb-DF： a large-scale challenging dataset for DeepFake forensics//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle，USA： IEEE： 3204-3213 ［DOI： 10.1109/CVPR42600.2020.00327］
Celeb-DF： a large-scale challenging dataset for DeepFake forensics
LiY Z，YangX，SunP，QiH G and LyuS W. 2019. Celeb-DF： a large-scale challenging dataset for DeepFake forensics ［EB/OL］. ［2026-01-10］.
https://arxiv.org/pdf/1909.12962.pdf
Depth map guided triplet network for deepfake face detection
LiangB Y，WangZ Y，HuangB J，ZouQ，WangQ and LiangJ J. 2023. Depth map guided triplet network for deepfake face detection. Neural Networks，159： 34-42 ［DOI： 10.1016/j.neunet.2022.11.031］
Meta-learning with relation embedding for few-shot deepfake detection
LiuX Y，SongP C，LuP and WangY J. 2024. Meta-learning with relation embedding for few-shot deepfake detection. IEEE Access，12： 180135-180145 ［DOI： 10.1109/ACCESS.2024.3499353］
Similarity quantification of bare footprint based on linear measurement and shape context contour combined score-based likelihood ratio evaluation
MaX，LuoY P，YuY，LiuY W，LiS and LiH M. 2024. Similarity quantification of bare footprint based on linear measurement and shape context contour combined score-based likelihood ratio evaluation. Forensic Science International，356： #111967 ［DOI： 10.1016/j.forsciint.2024.111967］
Improved likelihood ratios for face recognition in surveillance video by multimodal feature pairing
Macarulla RodriguezA，GeradtsZ，WorringM and UnzuetaL. 2024. Improved likelihood ratios for face recognition in surveillance video by multimodal feature pairing. Forensic Science International： Synergy，8： #100458 ［DOI： 10.1016/j.fsisyn.2024.100458］
Gotcha： real-time video deepfake detection via challenge-response
MittalG，HegdeC and MemonN. 2024. Gotcha： real-time video deepfake detection via challenge-response//Proceedings of 2024 IEEE 9th European Symposium on Security and Privacy （EuroS&P）： 1-20 ［DOI： 10.1109/EuroSP60621.2024.00009］
A comparison of procedures for the calculation of forensic likelihood ratios from acoustic-phonetic data： multivariate kernel density （MVKD） versus Gaussian mixture model-universal background model （GMM-UBM）
MorrisonG S. 2011. A comparison of procedures for the calculation of forensic likelihood ratios from acoustic-phonetic data： multivariate kernel density （MVKD） versus Gaussian mixture model-universal background model （GMM-UBM）. Speech Communication，53（2）： 242-256 ［DOI： 10.1016/j.specom.2010.09.005］
DeePhy： on deepfake phylogeny
NarayanK，AgarwalH，ThakralK，MittalS，VatsaM and SinghR. 2022. DeePhy： on deepfake phylogeny//Proceedings of 2022 IEEE International Joint Conference on Biometrics （IJCB）. Dhabi，United Arab Emirates： IEEE： 1-10 ［DOI： 10.1109/IJCB54206.2022.10007968］
GANprintR： improved fakes and evaluation of the state of the art in face manipulation detection
NevesJ C，TolosanaR，Vera-RodriguezR，LopesV，ProençaH and FierrezJ. 2020. GANprintR： improved fakes and evaluation of the state of the art in face manipulation detection. IEEE Journal of Selected Topics in Signal Processing，14（5）： 1038-1048 ［DOI： 10.1109/JSTSP.2020.3007250］
A deepfake detection algorithm based on fourier transform of biological signal
NiY，ZengW，XiaP，YangG S and TanR C. 2024. A deepfake detection algorithm based on fourier transform of biological signal. Computers，Materials and Continua，79（3）： 5295-5312 ［DOI： 10.32604/cmc.2024.049911］
DFGC 2021： a DeepFake game competition
PengB，FanH，WangW，DongJ，LiY and LyuS. 2021. DFGC 2021： a DeepFake game competition//Proceedings of 2021 IEEE International Joint Conference on Biometrics （IJCB）. Shenzhen，China： IEEE： 1-8 ［DOI： 10.1109/IJCB52358.2021.9484387］
Counterfactual image enhancement for explanation of face swap deepfakes
PengB，LyuS W，WangW and DongJ. 2022. Counterfactual image enhancement for explanation of face swap deepfakes//Proceedings of the 5th Chinese Conference on Pattern Recognition and Computer Vision. Shenzhen，China： Springer： 492-508. Lecture Notes in Computer Science，#13535 ［DOI： 10.1007/978-3-031-18910-4_40］
F2DLNet： a face forgery detection and localization network based on SSIM error maps
PengF，ZhangX L and LongM. 2023. F2DLNet： a face forgery detection and localization network based on SSIM error maps//Proceedings of the 4th International Conference on Machine Learning for Cyber Security. Guangzhou，China： Springer： 355-369 ［DOI： 10.1007/978-3-031-20099-1_30］
Deepfakes： a new content category for a digital age
PesetskiA. 2020. Deepfakes： a new content category for a digital age. The William and Mary Bill of Rights Journal，29（2）： 503-532
Fully unsupervised deepfake video detection via enhanced contrastive learning
QiaoT，XieS C，ChenY L，RetraintF and LuoX Y. 2024. Fully unsupervised deepfake video detection via enhanced contrastive learning. IEEE Transactions on Pattern Analysis and Machine Intelligence，46（7）： 4654-4668 ［DOI： 10.1109/TPAMI.2024.3356814］
DeepFake video detection： insights into model generalisation — a systematic review
RamanaharanR，GurugeD B and AgbinyaJ I. 2025. DeepFake video detection： insights into model generalisation — a systematic review. Data and Information Management： #100099 ［DOI： 10.1016/j.dim.2025.100099］
Deepfakes： the legal implications
RamluckanT. 2024. Deepfakes： the legal implications. International Conference on Cyber Warfare and Security，19（1）： 282-288 ［DOI： 10.34190/iccws.19.1.2099］
AI anomaly-based deepfake detection using customized mahalanobis distance and head pose with facial landmarks
RoscaC M and StancuA. 2025. AI anomaly-based deepfake detection using customized mahalanobis distance and head pose with facial landmarks. Applied Sciences，15（17）： #9574 ［DOI： 10.3390/app15179574］
FaceForensics++： learning to detect manipulated facial images
RösslerA，CozzolinoD，VerdolivaL，RiessC，ThiesJ and NiessnerM. 2019. FaceForensics++： learning to detect manipulated facial images//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul，Korea （South）： IEEE： 1-11 ［DOI： 10.1109/ICCV.2019.00009］
The liar’s dividend： can politicians claim misinformation to evade accountability？
SchiffK J，SchiffD S and BuenoN S. 2025. The liar’s dividend： can politicians claim misinformation to evade accountability？ American Political Science Review，119（1）： 71-90 ［DOI： 10.1017/S0003055423001454］
A comprehensive overview of deepfake： generation，detection，datasets，and opportunities
SeowJ W，LimM K，PhanR C W and LiuJ K. 2022. A comprehensive overview of deepfake： generation，detection，datasets，and opportunities. Neurocomputing，513： 351-371 ［DOI： 10.1016/j.neucom.2022.09.135］
AV-lip-sync+： leveraging AV-HuBERT to exploit multimodal inconsistency for deepfake detection of frontal face videos
ShahzadS A，HashmiA，PengY T，TsaoY and WangH M. 2025. AV-lip-sync+： leveraging AV-HuBERT to exploit multimodal inconsistency for deepfake detection of frontal face videos. IEEE Transactions on Human-Machine Systems，55（6）： 973-982 ［DOI： 10.1109/THMS.2025.3618409］
Sample based contrastive learning for DeepFake detection
ShaoC，ZhangF，WangJ X and ZhangB K. 2025. Sample based contrastive learning for DeepFake detection//Proceedings of the 2nd International Conference on Networks，Communications and Intelligent Computing （NCIC 2024）. Singapore，Singapore： Springer： 993-1000 ［DOI： 10.1007/978-981-96-5006-4_86］
Robustness and generalizability of deepfake detection： a study with diffusion models
SongH，HuangS，DongY and TuW. 2023. Robustness and generalizability of deepfake detection： a study with diffusion models ［EB/OL］. ［2026-01-10］.
https://arxiv.org/pdf/2309.02218.pdf
Evaluating likelihood ratio （LR） for firearm evidence identifications in forensic science based on the congruent matching cells （CMC） method
SongJ，ChenZ，VorburgerT V and SoonsJ A. 2020. Evaluating likelihood ratio （LR） for firearm evidence identifications in forensic science based on the congruent matching cells （CMC） method. Forensic Science International，317： #110502 ［DOI： 10.1016/j.forsciint.2020.110502］
DiffFake： exposing deepfakes using differential anomaly detection
StamnasS and SanchezV. 2025. DiffFake： exposing deepfakes using differential anomaly detection//Proceedings of 2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops （WACVW）. Tucson，USA： IEEE： 647-657 ［DOI： #10.1109/WACVW65960.2025.00079］
A two-stage interaction approach for enhancing generalization of deepfake detection
SunC L and LiW J. 2025. A two-stage interaction approach for enhancing generalization of deepfake detection. Multimedia Systems，31（5）： #359 ［DOI： 10.1007/s00530-025-01942-y］
Rethinking open-world DeepFake attribution with multi-perspective sensory learning
SunZ M，ChenS，YaoT P，YiR，DingS H and MaL Z. 2025. Rethinking open-world DeepFake attribution with multi-perspective sensory learning. International Journal of Computer Vision，133（2）： 628-651 ［DOI： 10.1007/s11263-024-02184-7］
Deepfakes： regulatory challenges for the synthetic society
Van Der Sloot B and Wagensveld Y. 2022. Deepfakes： regulatory challenges for the synthetic society. Computer Law & Security Review，46： #105716 ［DOI： 10.1016/j.clsr.2022.105716］
An overview of log likelihood ratio cost in forensic science-where is it used and what values can we expect？
Van LieropS，RamosD，SjerpsM and YpmaR. 2024. An overview of log likelihood ratio cost in forensic science-where is it used and what values can we expect？ Forensic Science International： Synergy，8： #100466 ［DOI： 10.1016/j.fsisyn.2024.100466］
Digital forensics，deepfakes，and the legal process
VenemaA E and GeradtsZ J. 2020. Digital forensics，deepfakes，and the legal process. Scitech Lawyer，16（4）： 14-17，23
Cross-domain deepfake detection based on latent domain knowledge distillation
WangC P，MengL S，XiaZ Q，RenN and MaB. 2025. Cross-domain deepfake detection based on latent domain knowledge distillation. IEEE Signal Processing Letters，32： 896-900 ［DOI： 10.1109/LSP.2025.3540941］
Exploring depth information for detecting manipulated face videos
WangH Y，LiS，HeJ，QianZ X，ZhangX P and FanS L. 2024. Exploring depth information for detecting manipulated face videos ［EB/OL］. ［2026-01-10］.
http://arxiv.org/pdf/2411.18572.pdf
Deepfake video detection based on image source anomaly
WangY F and LiaoG J. 2024. Deepfake video detection based on image source anomaly//Proceedings of the 2nd IEEE International Conference on Image Processing and Computer Applications （ICIPCA）. Shenyang，China： IEEE： 397-401 ［DOI： 10.1109/ICIPCA61593.2024.10709022］
Multi-attention-based approach for deepfake face and expression swap detection and localization
WaseemS，Abu-BakarS A R S，OmarZ，AhmedB A，BalochS and HafeezallahA. 2023. Multi-attention-based approach for deepfake face and expression swap detection and localization. EURASIP Journal on Image and Video Processing，2023（1）： #14 ［DOI： 10.1186/s13640-023-00614-z］
Analyzing fairness in deepfake detection with massively annotated databases
XuY，TerhörstP，PedersenM and RajaK. 2024a. Analyzing fairness in deepfake detection with massively annotated databases. IEEE Transactions on Technology and Society，5（1）： 93-106 ［DOI： 10.1109/TTS.2024.3365421］
Learning spatiotemporal inconsistency via thumbnail layout for face deepfake detection
XuY T，LiangJ，ShengL J and ZhangX Y. 2024b. Learning spatiotemporal inconsistency via thumbnail layout for face deepfake detection. International Journal of Computer Vision，132（12）： 5663-5680 ［DOI： 10.1007/s11263-024-02054-2］
Model-agnostic method： exposing deepfake using pixel-wise spatial and temporal fingerprints
YangJ，SunY R，MaoM Y，BaiL Z，ZhangS Y and WangF. 2023. Model-agnostic method： exposing deepfake using pixel-wise spatial and temporal fingerprints. IEEE Transactions on Big Data，9（6）： 1496-1509 ［DOI： 10.1109/TBDATA.2023.3284272］
Multi-level features global consistency for human facial deepfake detection
YangS C，WangJ，SunY L and TangJ H. 2022. Multi-level features global consistency for human facial deepfake detection. Journal of Image and Graphics，27（9）： 2708-2720
YangX，LiY and LyuS. 2019. Exposing deep fakes using inconsistent head poses//Proceedings of 2019 IEEE International Conference on Acoustics，Speech and Signal Processing （ICASSP）. Brighton，UK： IEEE： 8261-8265 ［DOI： 10.1109/ICASSP.2019.8683164］
SNIPPET： a framework for subjective evaluation of visual explanations applied to DeepFake detection
YangY Q，JoukovskyB，MogrovejoJ O，TuytelaarsT and DeligiannisN. 2024. SNIPPET： a framework for subjective evaluation of visual explanations applied to DeepFake detection. ACM Transactions on Multimedia Computing，Communications and Applications，20（8）： #253 ［DOI： 10.1145/3665248］
Review of research on face deepfake detection methods
YaoW D，LiP C，ZhaoY and WuH C. 2025. Review of research on face deepfake detection methods. Journal of Image and Graphics，30（7）： 2343-2363
Adversarial training and gradient optimization for partially deepfake audio localization
ZengS D，YiJ Y，TaoJ H，HeJ Y，LianZ，LiangS，et al. 2025. Adversarial training and gradient optimization for partially deepfake audio localization//Proceedings of 2025 IEEE International Conference on Acoustics，Speech and Signal Processing （ICASSP）. Hyderabad，India： IEEE： 1-5 ［DOI： 10.1109/ICASSP49660.2025.10890470］
Deepfake detection and localization using multi-view inconsistency measurement
ZhangB L，YinQ L，LuW and LuoX Y. 2025a. Deepfake detection and localization using multi-view inconsistency measurement. IEEE Transactions on Dependable and Secure Computing，22（2）： 1796-1809 ［DOI： 10.1109/TDSC.2024.3472064］
Federated learning-based cross-domain face forgery detection for consumer IOT systems
ZhangC H. 2025. Federated learning-based cross-domain face forgery detection for consumer IOT systems//Proceedings of the 4th International Conference on Electronic Information Engineering and Data Processing（Mohd Zain A B，Chen L，eds.） （EIEDP 2025. Kuala Lumpur，Malaysia： SPIE： #238 ［DOI： 10.1117/12.3067515］
FaceTracer： unveiling source identities from swapped face images and videos for fraud prevention
ZhangZ Y，ZhangJ，ZhouW B，ZhouX H，GuoQ，ZhangW M，et al. 2025b. FaceTracer： unveiling source identities from swapped face images and videos for fraud prevention. IEEE Transactions on Pattern Analysis and Machine Intelligence，47（12）： 12021-12037 ［DOI： 10.1109/TPAMI.2025.3601141］
ZhouC Z，ZhangD，ChenZ，ZhaoJ Q，ZhangG B and WeiC. 2025. A speaking face deepfake detection method，medium and device based on cross-modal learning： #CN120126223［P］. 2025
WildDeepfake： a challenging real-world dataset for deepfake detection
ZiB J，ChangM H，ChenJ J，MaX J and JiangY G. 2020. WildDeepfake： a challenging real-world dataset for deepfake detection//Proceedings of the 28th ACM International Conference on Multimedia： ［s.l.］： ［s.n.］
第 1 页 / 共 1 页
2026年第31卷第10期
PDF下载
20
8
引用本文
BibTeX
文章信息
doi: 10.11834/jig.250610
接收时间：2025-12-15
首发时间：2026-10-30
出版时间：2026-10-16
补充材料
相关文章
文章信息
作者
出版历史
收稿日期：2025-12-15
修回日期：2026-02-13
基金
Major Project of the National Social Science Fund of China （25&ZD238）；Graduate Research Project of People’s Public Security University of China （2024yjsky032）
全屏
文章导航
PDF下载
20
8
关闭全屏
北京市海淀区学院南路86号
010-62662699（运营及技术支持）
qkjq@cast.org.cn
