arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.02880cs.CR
收藏

Lotto:联邦学习中对抗恶意服务器的安全参与者选择机制

Lotto: Secure Participant Selection against Adversarial Servers in Federated Learning

Zhifeng Jiang, Peng Ye, Shiqi He, Wei Wang, Ruichuan Chen, Bo Li

AI总结:

针对联邦学习中恶意服务器可操控参与者选择破坏诚实多数假设的问题,提出Lotto系统,通过可验证随机自主参与、筛选池内随机近似知情选择实现安全选参,理论与实验验证其安全性与低开销。

摘要:

在联邦学习(FL)中,安全聚合、分布式差分隐私等常见隐私增强技术,都依赖于参与者中诚实方占多数这一关键假设,以此抵御各类攻击。但在实际场景中,服务器并非始终可信,恶意服务器可策略性地选择被攻陷的客户端,制造不诚实多数,进而破坏系统的安全保障。本文提出Lotto——一款联邦学习系统,通过实现可对抗恶意服务器的安全参与者选择,解决这一尚未被充分研究的核心问题。Lotto支持两种选择算法:随机选择与知情选择。为在无可信服务器的前提下保障随机选择,Lotto让每个客户端借助可验证随机性自主判定自身是否参与。对于更易被操控的知情选择,Lotto通过在筛选后的客户端池中执行随机选择,来近似实现知情选择算法。理论分析表明,Lotto可有效将服务器选出的被攻陷参与者比例,与群体中不诚实客户端的基础比率对齐。大规模实验进一步显示,Lotto的“达到目标精度所需时间”性能与非安全选择方法相当,说明安全选择的计算开销较低。

英文摘要:

In Federated Learning (FL), common privacy-enhancing techniques, such as secure aggregation and distributed differential privacy, rely on the critical assumption of an honest majority among participants to withstand various attacks. In practice, however, servers are not always trusted, and an adversarial server can strategically select compromised clients to create a dishonest majority, thereby undermining the system's security guarantees. In this paper, we present Lotto, an FL system that addresses this fundamental, yet underexplored issue by providing secure participant selection against an adversarial server. Lotto supports two selection algorithms: random and informed. To ensure random selection without a trusted server, Lotto enables each client to autonomously determine their participation using verifiable randomness. For informed selection, which is more vulnerable to manipulation, Lotto approximates the algorithm by employing random selection within a refined client pool. Our theoretical analysis shows that Lotto effectively aligns the proportion of server-selected compromised participants with the base rate of dishonest clients in the population. Large-scale experiments further reveal that Lotto achieves time-to-accuracy performance comparable to that of insecure selection methods, indicating a low computational overhead for secure selection.

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。

↑