arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.02131cs.CRcs.LG
收藏

联邦学习中的模型劫持攻击

Model Hijacking Attack in Federated Learning

CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);Nokia Bell Labs(诺基亚贝尔实验室)

Zheng Li, Siyuan Wu, Ruichuan Chen, Paarijaat Aditya, Istemi Ekin Akkus, Manohar Vanga, Min Zhang, Hao Li, Yang Zhang

AI总结:

本文提出首个针对联邦学习全局模型的劫持攻击HijackFL,通过像素级伪装使劫持样本对齐原始特征空间,实验证明其攻击效果优于基线。

摘要:

机器学习(ML)在集中式学习和联邦学习等重要范式的推动下,已在从自动驾驶到人脸识别的各类关键应用中取得显著进展。然而,其显著成功也伴随着各种攻击。近来,模型劫持攻击表明,ML模型可能被劫持以执行与其原始任务不同的任务,这增加了问责风险和寄生计算风险。尽管如此,迄今为止这种攻击仅聚焦于集中式学习。在本工作中,我们将该攻击的范围扩展到联邦学习领域,在该领域中多个客户端在不共享其数据的情况下协同训练一个全局模型。具体而言,我们提出了HijackFL,这是首个针对联邦学习中全局模型的此类劫持攻击。攻击者旨在迫使全局模型执行与其原始任务不同的任务(称为劫持任务),而不被服务器或良性客户端察觉。为实现这一目标,与现有使用数据投毒来修改目标模型参数的方法不同,HijackFL基于其本地模型(不作修改)搜索像素级扰动,以使劫持样本在特征空间中与原始样本对齐。在执行劫持任务时,攻击者将这些伪装应用于劫持样本,迫使全局模型将其识别为原始样本并据此进行预测。我们在四个基准数据集和三种流行模型上开展了大量实验。实证结果表明,其攻击性能优于基线方法。我们进一步研究了影响其性能的因素,并讨论了可缓解其影响的可能防御措施。

英文摘要:

Machine learning (ML), driven by prominent paradigms such as centralized and federated learning, has made significant progress in various critical applications ranging from autonomous driving to face recognition. However, its remarkable success has been accompanied by various attacks. Recently, the model hijacking attack has shown that ML models can be hijacked to execute tasks different from their original tasks, which increases both accountability and parasitic computational risks. Nevertheless, thus far, this attack has only focused on centralized learning. In this work, we broaden the scope of this attack to the federated learning domain, where multiple clients collaboratively train a global model without sharing their data. Specifically, we present HijackFL, the first-of-its-kind hijacking attack against the global model in federated learning. The adversary aims to force the global model to perform a different task (called hijacking task) from its original task without the server or benign client noticing. To accomplish this, unlike existing methods that use data poisoning to modify the target model's parameters, HijackFL searches for pixel-level perturbations based on their local model (without modifications) to align hijacking samples with the original ones in the feature space. When performing the hijacking task, the adversary applies these cloaks to the hijacking samples, compelling the global model to identify them as original samples and predict them accordingly. We conduct extensive experiments on four benchmark datasets and three popular models. Empirical results demonstrate that its attack performance outperforms baselines. We further investigate the factors that affect its performance and discuss possible defenses to mitigate its impact.

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。

↑