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 2407.19703cs.CR
收藏

高效的拜占庭鲁棒且可证明隐私保护的联邦学习

Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning

Chenfei Nie, Qiang Li, Yuxin Yang, Yuede Ji, Binghui Wang

AI总结:

提出BPFL方法,结合零知识证明与同态加密,在联邦学习中同时实现拜占庭鲁棒性与可证明的隐私保护,且保持高效性。

摘要:

联邦学习(FL)是一种新兴的分布式学习范式,无需共享参与客户端的私有数据。然而,现有研究表明,FL容易受到拜占庭(安全)攻击和数据重构(隐私)攻击。几乎所有现有的FL防御方法仅解决这两种攻击中的一种。少数防御方法同时应对这两种攻击,但效率和有效性不足。我们提出BPFL,一种高效的拜占庭鲁棒且可证明隐私保护的FL方法,解决所有上述问题。具体而言,我们借鉴最先进的拜占庭鲁棒FL方法,并使用相似性度量来衡量FL中每个参与客户端的鲁棒性。客户端的有效性被表述为相似性度量的电路约束,并通过零知识证明进行验证。此外,客户端模型由共享随机向量掩蔽,该向量基于同态加密生成。如此,服务器接收到的是掩蔽后的客户端模型而非真实模型,后者被证明是隐私的。由于使用非交互式零知识证明,BPFL也具有高效性。在多个数据集上的实验结果表明,我们的BPFL是高效的、拜占庭鲁棒的且隐私保护的。

英文摘要:

Federated learning (FL) is an emerging distributed learning paradigm without sharing participating clients' private data. However, existing works show that FL is vulnerable to both Byzantine (security) attacks and data reconstruction (privacy) attacks. Almost all the existing FL defenses only address one of the two attacks. A few defenses address the two attacks, but they are not efficient and effective enough. We propose BPFL, an efficient Byzantine-robust and provably privacy-preserving FL method that addresses all the issues. Specifically, we draw on state-of-the-art Byzantine-robust FL methods and use similarity metrics to measure the robustness of each participating client in FL. The validity of clients are formulated as circuit constraints on similarity metrics and verified via a zero-knowledge proof. Moreover, the client models are masked by a shared random vector, which is generated based on homomorphic encryption. In doing so, the server receives the masked client models rather than the true ones, which are proven to be private. BPFL is also efficient due to the usage of non-interactive zero-knowledge proof. Experimental results on various datasets show that our BPFL is efficient, Byzantine-robust, and privacy-preserving.

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。

↑