arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.00540cs.CR
收藏

面向大规模网络的可扩展且鲁棒的联邦学习压缩私有聚合

Compressed Private Aggregation for Scalable and Robust Federated Learning over Massive Networks

Natalie Lang, Nir Shlezinger, Rafael G. L. D'Oliveira, Salim El Rouayheb

AI总结:

本文提出压缩私有聚合(CPA)方法,通过嵌套格量化和码本随机化,在极低比特率下同时实现联邦学习的隐私保护、匿名性和抗恶意用户鲁棒性,且保持与无隐私压缩FL相同的渐近收敛速率。

摘要:

联邦学习(FL)是一种新兴范式,允许中央服务器利用远程用户的数据训练机器学习模型。尽管其日益流行,FL在保护本地数据集隐私、抵御恶意用户的投毒攻击以及通信开销方面面临挑战。在大规模网络中,通信开销尤为显著。这些局限性通常分别通过本地差分隐私(LDP)机制、鲁棒聚合、压缩和用户选择技术来缓解,而这些技术往往以牺牲精度为代价。在本文中,我们提出了压缩私有聚合(CPA),使大规模部署能够以极低的比特率同时进行通信,同时实现隐私性、匿名性和对恶意用户的鲁棒性。CPA利用嵌套格量化器将数据压缩为少量比特,并对码本进行随机化处理,在确保匿名性和鲁棒性的同时,通过后续扰动保持LDP。经证明,所提出的CPA能够使FL以与未考虑隐私、压缩和鲁棒性的FL相同的渐近速率收敛,同时满足匿名性和LDP要求。这些分析性质在数值研究中得到了实证验证,我们展示了CPA与单独的压缩和隐私机制相比在训练不同图像分类模型时的性能增益,以及其在减轻恶意用户有害影响方面的鲁棒性。

英文摘要:

Federated learning (FL) is an emerging paradigm that allows a central server to train machine learning models using remote users' data. Despite its growing popularity, FL faces challenges in preserving the privacy of local datasets, its sensitivity to poisoning attacks by malicious users, and its communication overhead. The latter is additionally considerably dominant in large-scale networks. These limitations are often individually mitigated by local differential privacy (LDP) mechanisms, robust aggregation, compression, and user selection techniques, which typically come at the cost of accuracy. In this work, we present compressed private aggregation (CPA), that allows massive deployments to simultaneously communicate at extremely low bit rates while achieving privacy, anonymity, and resilience to malicious users. CPA randomizes a codebook for compressing the data into a few bits using nested lattice quantizers, while ensuring anonymity and robustness, with a subsequent perturbation to hold LDP. The proposed CPA is proven to result in FL convergence in the same asymptotic rate as FL without privacy, compression, and robustness considerations, while satisfying both anonymity and LDP requirements. These analytical properties are empirically confirmed in a numerical study, where we demonstrate the performance gains of CPA compared with separate mechanisms for compression and privacy for training different image classification models, as well as its robustness in mitigating the harmful effects of malicious users.

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。

↑