东华大学学报（英文版）2026，Vol.43Issue(1)：50-58,9.DOI:10.19884/j.1672-5220.202412010
基于联邦学习的自适应模拟后门攻击
Adaptive Simulation Backdoor Attack Based on Federated Learning
石秀金 1夏凯雄 1颜帼英 2谈轩 1孙延旭 1朱小龙1
作者信息
- 1. 东华大学 计算机科学与技术学院,上海 201620
- 2. 东华大学 外语学院,上海 201620
- 折叠
摘要
Abstract
In federated learning,backdoor attacks have become an important research topic with their wide application in processing sensitive datasets.Since federated learning detects or modifies local models through defense mechanisms during aggregation,it is difficult to conduct effective backdoor attacks.In addition,existing backdoor attack methods are faced with challenges,such as low backdoor accuracy,poor ability to evade anomaly detection,and unstable model training.To address these challenges,a method called adaptive simulation backdoor attack(ASBA)is proposed.Specifically,ASBA improves the stability of model training by manipulating the local training process and using an adaptive mechanism,the ability of the malicious model to evade anomaly detection by combing large simulation training and clipping,and the backdoor accuracy by introducing a stimulus model to amplify the impact of the backdoor in the global model.Extensive comparative experiments under five advanced defense scenarios show that ASBA can effectively evade anomaly detection and achieve high backdoor accuracy in the global model.Furthermore,it exhibits excellent stability and effectiveness after multiple rounds of attacks,outperforming state-of-the-art backdoor attack methods.关键词
联邦学习/后门攻击/隐私/自适应攻击/模拟Key words
federated learning/backdoor attack/privacy/adaptive attack/simulation分类
信息技术与安全科学引用本文复制引用
石秀金,夏凯雄,颜帼英,谈轩,孙延旭,朱小龙..基于联邦学习的自适应模拟后门攻击[J].东华大学学报（英文版）,2026,43(1):50-58,9.
