Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning

43RD IEEE SYMPOSIUM ON SECURITY AND PRIVACY (SP 2022)(2022)

引用 152|浏览7
暂无评分
摘要
While recent works have indicated that federated learning (FL) may be vulnerable to poisoning attacks by compromised clients, their real impact on production FL systems is not fully understood. In this work, we aim to develop a comprehensive systemization for poisoning attacks on FL by enumerating all possible threat models, variations of poisoning, and adversary capabilities. We specifically put our focus on untargeted poisoning attacks, as we argue that they are significantly relevant to production FL deployments. We present a critical analysis of untargeted poisoning attacks under practical, production FL environments by carefully characterizing the set of realistic threat models and adversarial capabilities. Our findings are rather surprising: contrary to the established belief, we show that FL is highly robust in practice even when using simple, low-cost defenses. We go even further and propose novel, state-of-the-art data and model poisoning attacks, and show via an extensive set of experiments across three benchmark datasets how (in)effective poisoning attacks are in the presence of simple defense mechanisms. We aim to correct previous misconceptions and offer concrete guidelines to conduct more accurate (and more realistic) research on this topic.
更多
查看译文
关键词
production federated learning,poisoning attacks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要