Skip to yearly menu bar Skip to main content


Virtual presentation / poster accept

FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning

Kaiyuan Zhang · Guanhong Tao · Qiuling Xu · Siyuan Cheng · Shengwei An · Yingqi Liu · Shiwei Feng · Guangyu Shen · Pin-Yu Chen · Shiqing Ma · Xiangyu Zhang

Keywords: [ federated learning ] [ backdoor mitigation ] [ General Machine Learning ]


Abstract:

Federated Learning (FL) is a distributed learning paradigm that enables different parties to train a model together for high quality and strong privacy protection. In this scenario, individual participants may get compromised and perform backdoor attacks by poisoning the data (or gradients). Existing work on robust aggregation and certified FL robustness does not study how hardening benign clients can affect the global model (and the malicious clients). In this work, we theoretically analyze the connection among cross-entropy loss, attack success rate, and clean accuracy in this setting. Moreover, we propose a trigger reverse engineering based defense and show that our method can achieve robustness improvement with guarantee (i.e., reducing the attack success rate) without affecting benign accuracy. We conduct comprehensive experiments across different datasets and attack settings. Our results on nine competing SOTA defense methods show the empirical superiority of our method on both single-shot and continuous FL backdoor attacks. Code is available at https://github.com/KaiyuanZh/FLIP.

Chat is not available.