收藏切换
Survey of Backdoor Attack and Defense Algorithms Based on Federated Learning
收藏切换
Jialang Liu, Yanming Guo*, Mingrui Lao, Tianyuan Yu, Yulun Wu, Yunhao Feng, Jiazhuang Wu
Journal of Computer Research and Development | 2024, 61(10) : 2607 - 2626
Less
收藏切换
Journal of Computer Research and Development | 2024, 61(10): 2607-2626
• Artificial Intelligence Security for Data Elements •
Survey of Backdoor Attack and Defense Algorithms Based on Federated Learning
Full
Jialang Liu, Yanming Guo*, Mingrui Lao, Tianyuan Yu, Yulun Wu, Yunhao Feng, Jiazhuang Wu
Affiliations
  • Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000
  • born in 1999. Master cadidate. His main research interests include federated learning, backdoor attack, and deep learning

    born in 1989. Associate professor. His main research interests include deep learning, cross-media information processing, and intelligent adversarial attack

    born in 1995, PhD, lecturer. His main research interests include cross-media data analysis, and data security and adversarial attack defense

    born in 1992. PhD. His main research interests include computer vision, federated learning, and visual language modeling

    born in 1996. PhD candidate. His main research interests include adversarial machine learning, trustworthy AI, and multimodal deep learning

    born in 2002. PhD candidate. His main research interests include trustworthy security of artificial intelligence, adversarial robustness, and federated algorithms

    born in 2001. Master candidate. His main research interests include adversarial examples and federated learning

About Author:

born in 1999. Master cadidate. His main research interests include federated learning, backdoor attack, and deep learning

born in 1989. Associate professor. His main research interests include deep learning, cross-media information processing, and intelligent adversarial attack

born in 1995, PhD, lecturer. His main research interests include cross-media data analysis, and data security and adversarial attack defense

born in 1992. PhD. His main research interests include computer vision, federated learning, and visual language modeling

born in 1996. PhD candidate. His main research interests include adversarial machine learning, trustworthy AI, and multimodal deep learning

born in 2002. PhD candidate. His main research interests include trustworthy security of artificial intelligence, adversarial robustness, and federated algorithms

born in 2001. Master candidate. His main research interests include adversarial examples and federated learning

Published: 2024-10-01 doi: 10.7544/issn1000-1239.202440487
Outline
收藏切换

Federated learning is designed for data privacy and data security issues, after a large number of clients are trained locally in a distributed manner, the central server then aggregates the model parameter updates provided by each local client, but the central server is unable to see how these parameters are updated, and this feature creates a serious security issue, i.e., a malicious participant can train a poisoned model and upload the parameters in the local model, and then globally model to introduce backdoor features. In this paper, we focus on the security and robustness research under the scenarios specific to federated learning, i.e., backdoor attack and defense, summarize the scenarios that generate backdoor attacks under federated learning, summarize the latest methods of backdoor attack and defense under federated learning, and compare and analyze the performance of the various attack and defense methods, revealing their advantages and limitations. Finally, we point out various potential directions and new challenges for backdoor attacks and defenses under federated learning.

federated learning  /  backdoor attack  /  backdoor defense  /  data privacy  /  data security
刘嘉浪, 郭延明, 老明瑞, 于天元, 武与伦, 冯云浩, 吴嘉壮. 基于联邦学习的后门攻击与防御算法综述. 计算机研究与发展, 2024 , 61 (10) : 2607 -2626 . DOI: 10.7544/issn1000-1239.202440487
Jialang Liu, Yanming Guo, Mingrui Lao, Tianyuan Yu, Yulun Wu, Yunhao Feng, Jiazhuang Wu. Survey of Backdoor Attack and Defense Algorithms Based on Federated Learning[J]. Journal of Computer Research and Development, 2024 , 61 (10) : 2607 -2626 . DOI: 10.7544/issn1000-1239.202440487
Year 2024 volume 61 Issue 10
77
37
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202440487
  • Receive Date:2024-06-06
  • Online Date:2026-11-17
  • Published:2024-10-01
Article Data
Affiliations
History
  • Received:2024-06-06
  • Revised:2024-07-19
Affiliations
    Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440487
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