arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.09209cs.CRcs.AI
收藏

FLDetector:通过检测恶意客户端防御联邦学习模型中毒攻击

FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients

University of Science and Technology of China(中国科学技术大学);Duke University(杜克大学)

Zaixi Zhang, Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

摘要:

联邦学习(FL)容易受到模型中毒攻击,恶意客户端通过向服务器发送修改后的模型更新来破坏全局模型。现有的防御主要依赖于拜占庭健壮的FL方法,其目的是学习一个准确的全局模型,即使一些客户端是恶意的。然而,它们在实践中只能抵抗少数恶意客户端。如何抵御大量恶意客户端的模型中毒攻击仍然是一个开放的挑战。我们的FLDetector通过检测恶意客户端来解决这一挑战。FLDetector旨在检测和删除大多数恶意客户端,以便Byzantine-robust FL方法可以使用剩余的客户端学习准确的全局模型。我们的主要观察是,在模型中毒攻击中,来自客户端的模型更新在多次迭代中是不一致的。因此,FLDetector通过检查其模型更新一致性来检测恶意客户端。粗略地说,服务器使用柯西中值定理和L-BFGS基于客户端的历史模型更新来预测客户端在每次迭代中的模型更新,并且如果从客户端接收的模型更新和预测的模型更新在多次迭代中不一致,则将客户端标记为恶意。我们在三个基准数据集上进行的大量实验表明,FLDetector可以在多种最先进的模型中毒攻击中准确检测恶意客户端。在删除检测到的恶意客户端后,现有的Byzantine-robust FL方法可以学习准确的全局模型。我们的代码可以在https://github.com/zaixizhang/FLDetector上找到。

英文摘要:

Federated learning (FL) is vulnerable to model poisoning attacks, in which malicious clients corrupt the global model via sending manipulated model updates to the server. Existing defenses mainly rely on Byzantine-robust FL methods, which aim to learn an accurate global model even if some clients are malicious. However, they can only resist a small number of malicious clients in practice. It is still an open challenge how to defend against model poisoning attacks with a large number of malicious clients. Our FLDetector addresses this challenge via detecting malicious clients. FLDetector aims to detect and remove the majority of the malicious clients such that a Byzantine-robust FL method can learn an accurate global model using the remaining clients. Our key observation is that, in model poisoning attacks, the model updates from a client in multiple iterations are inconsistent. Therefore, FLDetector detects malicious clients via checking their model-updates consistency. Roughly speaking, the server predicts a client's model update in each iteration based on its historical model updates using the Cauchy mean value theorem and L-BFGS, and flags a client as malicious if the received model update from the client and the predicted model update are inconsistent in multiple iterations. Our extensive experiments on three benchmark datasets show that FLDetector can accurately detect malicious clients in multiple state-of-the-art model poisoning attacks. After removing the detected malicious clients, existing Byzantine-robust FL methods can learn accurate global models.Our code is available at https://github.com/zaixizhang/FLDetector.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑