arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.09897cs.CRcs.AIcs.MA
收藏

具有不经意分布式差分隐私的抗合谋联邦学习

Collusion Resistant Federated Learning with Oblivious Distributed Differential Privacy

Bowdoin College(鲍登学院);Massachusetts Institute of Technology(麻省理工学院);J.P. Morgan AI Research(摩根大通人工智能研究院)

David Byrd, Vaikkunth Mugunthan, Antigoni Polychroniadou, Tucker Hybinette Balch

摘要:

隐私保护联邦学习使分布式客户端能够共同学习共享模型,同时保持客户端训练数据的私密性,即使来自不受信任的服务器。先前的工作没有提供有效的解决方案,防止共谋攻击,其中各方合作,以暴露一个诚实的客户端的模型参数。我们提出了一个有效的机制,基于不经意的分布式差分隐私,这是第一个防止这种客户端勾结,包括“西比尔”攻击,其中服务器优先选择受损的设备或模拟假设备。我们利用新的隐私机制,构建一个安全的联邦学习协议,并证明该协议的安全性。我们得出结论,在5,000个分布式网络客户端的现实模拟的两个数据集上的协议的执行速度,学习精度和隐私性能的实证分析。

英文摘要:

Privacy-preserving federated learning enables a population of distributed clients to jointly learn a shared model while keeping client training data private, even from an untrusted server. Prior works do not provide efficient solutions that protect against collusion attacks in which parties collaborate to expose an honest client's model parameters. We present an efficient mechanism based on oblivious distributed differential privacy that is the first to protect against such client collusion, including the "Sybil" attack in which a server preferentially selects compromised devices or simulates fake devices. We leverage the novel privacy mechanism to construct a secure federated learning protocol and prove the security of that protocol. We conclude with empirical analysis of the protocol's execution speed, learning accuracy, and privacy performance on two data sets within a realistic simulation of 5,000 distributed network clients.

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。

↑