arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.04899cs.CR
收藏

DIST-FL:增强联邦学习中基于TEE的聚合安全性

DIST-FL: Enhancing Security for TEE-based Aggregation in Federated Learning

Research Institute of Trustworthy Autonomous Systems and the Department of Computer Science and Engineering, Southern University of Science and Technology(南方科技大学可信自主系统研究院与计算机科学与工程系);School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机学院);Ping An Technology (Shenzhen) Co., Ltd.(平安科技(深圳)有限公司)

Guanlong Wu, Ju Yang, Zhen Huang, Jianyu Niu, Guoxing Chen, Jianzong Wang, Yinqian Zhang

AI总结:

针对服务器端对手利用TEE局限性(状态回滚和I/O操纵)攻击联邦学习的问题,提出DIST-FL分布式多TEE系统,通过操作线性化和可靠服务器输入实现鲁棒聚合,性能与单TEE相当且吞吐量提升6倍。

摘要:

可信执行环境(TEE)辅助的联邦学习协议成为应对服务器端对手并确保服务器可信性的有前途的解决方案。在本文中,我们剖析了现有协议,并证明服务器端对手仍可通过利用TEE的局限性(即状态回滚和I/O操纵)操纵客户端选择和重放聚合,从而破坏系统鲁棒性和隐私性。为此,我们提出了DIST-FL,一个由多个TEE守护的服务器分布式系统,形成仅追加账本,用于隐私保护且鲁棒的联邦学习聚合。具体而言,DIST-FL确保操作线性化以阻止状态回滚攻击,并整合来自可靠服务器的输入以缓解I/O操纵威胁。我们实现了DIST-FL并在广域网设置下进行了评估。实验结果表明,DIST-FL能有效应对所提出的攻击,性能与单TEE相当,同时利用TEE的计算优势,吞吐量比同类方案提升6倍。

英文摘要:

Trusted Execution Environments (TEEs)-aided federated learning protocols emerge as promising solutions to counter server-side adversaries and ensure the trustworthiness of the server. In this paper, we dissect existing protocols and demonstrate that server-side adversaries can still manipulate client selection and replay aggregation to compromise system robustness and privacy, by exploiting TEE limitations, i.e., state rollback and I/O manipulation. To this end, we present DIST-FL, a distributed system of servers guarded by multiple TEEs forming an append-only ledger for privacy-preserved, robust FL aggregation. Specifically, DIST-FL ensures operation linearizability to thwart state rollback attacks and incorporates inputs from reliable servers to mitigate I/O manipulation threats. We implement DIST-FL and conduct evaluations in WAN settings. Experimental results demonstrate that DIST-FL can effectively counter the proposed attacks and match the single-TEE's performance while offering a 6x throughput boost over its counterparts, leveraging TEE's computational advantages.

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。

↑