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 2307.00543cs.LGcs.AIcs.CRcs.GT
收藏

基于区块链的联邦学习投毒攻击防御

Defending Against Poisoning Attacks in Federated Learning with Blockchain

Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Imperial College London(帝国理工学院);UiT The Arctic University of Norway(挪威北极大学);Carnegie Mellon University(卡内基梅隆大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

Nanqing Dong, Zhipeng Wang, Jiahao Sun, Michael Kampffmeyer, William Knottenbelt, Eric Xing

AI总结:

针对联邦学习依赖中心化服务器存在单点故障、易受恶意客户端投毒攻击的问题,提出基于区块链与分布式账本、由链上智能合约驱动点对点投票及奖惩机制的安全联邦学习系统,经理论与实验验证对恶意客户端行为具备鲁棒性。

摘要:

在深度学习时代,联邦学习(FL)是一种颇具前景的方法,可让多机构数据所有者(即客户端)在不损害数据隐私的情况下协同训练机器学习模型。但现有大多数联邦学习方法依赖中心化服务器进行全局模型聚合,存在单点故障问题,导致系统在应对不诚实客户端时易受恶意攻击。本文针对这一问题,提出了一种基于区块链与分布式账本技术的安全可靠联邦学习系统。该系统融合了点对点投票机制与奖惩机制,二者均由链上智能合约驱动,用于检测并遏制恶意行为。本文通过理论分析与实证分析验证了所提方法的有效性,结果表明该框架对恶意客户端行为具备鲁棒性。

英文摘要:

In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owners, or clients, to collaboratively train machine learning models without compromising data privacy. However, most existing FL approaches rely on a centralized server for global model aggregation, leading to a single point of failure. This makes the system vulnerable to malicious attacks when dealing with dishonest clients. In this work, we address this problem by proposing a secure and reliable FL system based on blockchain and distributed ledger technology. Our system incorporates a peer-to-peer voting mechanism and a reward-and-slash mechanism, which are powered by on-chain smart contracts, to detect and deter malicious behaviors. Both theoretical and empirical analyses are presented to demonstrate the effectiveness of the proposed approach, showing that our framework is robust against malicious client-side behaviors.

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。

↑