Towards Attack-tolerant Federated Learning via Critical Parameter Analysis

Autor:	Han, Sungwon, Park, Sungwon, Wu, Fangzhao, Kim, Sundong, Zhu, Bin, Xie, Xing, Cha, Meeyoung
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Cryptography and Security
Druh dokumentu:	Working Paper
Popis:	Federated learning is used to train a shared model in a decentralized way without clients sharing private data with each other. Federated learning systems are susceptible to poisoning attacks when malicious clients send false updates to the central server. Existing defense strategies are ineffective under non-IID data settings. This paper proposes a new defense strategy, FedCPA (Federated learning with Critical Parameter Analysis). Our attack-tolerant aggregation method is based on the observation that benign local models have similar sets of top-k and bottom-k critical parameters, whereas poisoned local models do not. Experiments with different attack scenarios on multiple datasets demonstrate that our model outperforms existing defense strategies in defending against poisoning attacks. Comment: ICCV'23 Accepted
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2308.09318 Zobrazit plný text záznamu View this record from Arxiv