收藏切换
Phonemic Adversarial Attack Against Audio Recognition in Physical World
收藏切换
Jiakai Wang1, 2, Yusheng Kong1, 3, Zhendong Chen4, 5, Jin Hu2, Zixin Yin2, Yuqing Ma2, Qinghong Yang5, Xianglong Liu1, 2, 6, *
Journal of Computer Research and Development | 2025, 62(3) : 751 - 764
Less
收藏切换
Journal of Computer Research and Development | 2025, 62(3): 751-764
• Network and Information Security •
Phonemic Adversarial Attack Against Audio Recognition in Physical World
Full
Jiakai Wang1, 2, Yusheng Kong1, 3, Zhendong Chen4, 5, Jin Hu2, Zixin Yin2, Yuqing Ma2, Qinghong Yang5, Xianglong Liu1, 2, 6, *
Affiliations
  • 1Beijing Zhongguancun Laboratory, Beijing 100194
  • 2State Key Laboratory of Complex and Critical Software Environment (Beihang University), Beijing 100191
  • 3School of Automation Science and Electric Engineering, Beihang University, Beijing 100191
  • 4Polixir Technologies, Nanjing 211106
  • 5School of Software, Beihang University, Beijing 100191
  • 6Institute of Data Space, Hefei Comprehensive National Science Center, Hefei 231200
  • born in 1995. PhD, associate professor. His mian research interests include physical adversarial attacks and defenses, model security evaluation, and trustworthy AI

    born in 1995. PhD candidate, engineer. His main research interests include physical adversarial attacks and defenses, industrial artificial intelligence, and IIoT cyber security

    born in 1998. Master, assistant engineer. His main research interest includes the audio adversarial attack

    born in 2000. PhD candidate. His main research interests include physical adversarial attacks, AI attack and defense simulation, and trustworthy artificial intelligence

    born in 1999. Master. His main research interests include physical adversarial attacks and defenses, and trustworthy artificial intelligence

    born in 1992. PhD, associate professor. Her main research interests include open-world learning, model generalization, and trustworthy AI

    born in 1974. PhD, professor of engineering, PhD supervisor. Her main research interests include software engineering and artificial intelligence

    born in 1985. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include machine learning, computer vision, and multimedia information retrieval

About Author:

born in 1995. PhD, associate professor. His mian research interests include physical adversarial attacks and defenses, model security evaluation, and trustworthy AI

born in 1995. PhD candidate, engineer. His main research interests include physical adversarial attacks and defenses, industrial artificial intelligence, and IIoT cyber security

born in 1998. Master, assistant engineer. His main research interest includes the audio adversarial attack

born in 2000. PhD candidate. His main research interests include physical adversarial attacks, AI attack and defense simulation, and trustworthy artificial intelligence

born in 1999. Master. His main research interests include physical adversarial attacks and defenses, and trustworthy artificial intelligence

born in 1992. PhD, associate professor. Her main research interests include open-world learning, model generalization, and trustworthy AI

born in 1974. PhD, professor of engineering, PhD supervisor. Her main research interests include software engineering and artificial intelligence

born in 1985. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include machine learning, computer vision, and multimedia information retrieval

Published: 2025-03-01 doi: 10.7544/issn1000-1239.202330445
Outline
收藏切换

Audio recognition has been widely applied in the typical scenarios, like auto-driving, Internet of things, and etc. In recent years, research on adversarial attacks in audio recognition has attracted extensive attention. However, most of the existing studies mainly rely on the coarse-grain audio features at the instance level, which leads to expensive generation time costs and weak universal attacking ability in real world. To address the problem, we propose a phonemic adversarial noise (PAN) generation paradigm, which exploits the audio features at the phoneme level to perform fast and universal adversarial attacks. Experiments are conducted using a variety of datasets commonly used in speech recognition tasks, such as LibriSpeech, to experimentally validate the effectiveness of the PAN proposed in this paper, its ability to generalize across datasets, its ability to migrate attacks across models, and its ability to migrate attacks across tasks, as well as further validating the effectiveness of the attack civilian-oriented Internet of things audio recognition application in the physical world devices. Extensive experiments demonstrate that the proposed PAN outperforms the comparative baselines by large margins (about 24 times speedup and 38% attacking ability improvement on average), and the sampling strategy and learning method proposed in this paper are significant in reducing the training time and improving the attack capability.

security of artificial intelligence  /  adversarial attack  /  audio recognition  /  physical attack  /  phonemic adversarial noise
王嘉凯, 孔宇升, 陈镇东, 胡琎, 尹子鑫, 马宇晴, 杨晴虹, 刘祥龙. 针对音频识别的物理世界音素对抗攻击. 计算机研究与发展, 2025 , 62 (3) : 751 -764 . DOI: 10.7544/issn1000-1239.202330445
Jiakai Wang, Yusheng Kong, Zhendong Chen, Jin Hu, Zixin Yin, Yuqing Ma, Qinghong Yang, Xianglong Liu. Phonemic Adversarial Attack Against Audio Recognition in Physical World[J]. Journal of Computer Research and Development, 2025 , 62 (3) : 751 -764 . DOI: 10.7544/issn1000-1239.202330445
Year 2025 volume 62 Issue 3
128
48
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202330445
  • Receive Date:2023-06-05
  • Online Date:2026-11-10
  • Published:2025-03-01
Article Data
Affiliations
History
  • Received:2023-06-05
  • Revised:2024-05-10
  • Accepted:2024-06-07
Affiliations
    1Beijing Zhongguancun Laboratory, Beijing 100194
    2State Key Laboratory of Complex and Critical Software Environment (Beihang University), Beijing 100191
    3School of Automation Science and Electric Engineering, Beihang University, Beijing 100191
    4Polixir Technologies, Nanjing 211106
    5School of Software, Beihang University, Beijing 100191
    6Institute of Data Space, Hefei Comprehensive National Science Center, Hefei 231200
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202330445
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT