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 2202.07178cs.LGcs.CR
收藏

基于稀疏模型扰动的联邦学习:提高客户端差分隐私下的准确性

Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy

University of Nevada, Reno(内华达大学雷诺分校);University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校)

Rui Hu, Yanmin Gong, Yuanxiong Guo

摘要:

联邦学习(FL)使边缘设备能够协作地学习共享模型,同时将其训练数据保持在本地,近来受到了极大的关注,并且与传统的集中式学习范式相比,它可以保护隐私。然而,关于训练数据的敏感信息仍然可以从FL中共享的模型参数中推断出来。差分隐私(DP)是防御这些攻击的最新技术。在FL中实现DP的关键挑战在于DP噪声对模型精度的不利影响,特别是对于具有大量参数的深度学习模型。本文提出了一种新的差分私有FL方案Fed-SMP,它在保持高模型精度的同时提供了客户端级的DP保证。为了减轻隐私保护对模型准确性的影响,Fed-SMP利用了一种名为稀疏模型扰动(SMP)的新技术,在该技术中,本地模型在被高斯噪声扰动之前首先被稀疏化。我们提供了一个紧密的端到端的隐私分析Fed-SMP使用Renyi DP,并证明了收敛的Fed-SMP与无偏和有偏稀疏。在真实数据集上进行了大量的实验,以证明Fed-SMP在提高模型精度的同时,具有相同的DP保证和节省通信成本的有效性。

英文摘要:

Federated learning (FL) that enables edge devices to collaboratively learn a shared model while keeping their training data locally has received great attention recently and can protect privacy in comparison with the traditional centralized learning paradigm. However, sensitive information about the training data can still be inferred from model parameters shared in FL. Differential privacy (DP) is the state-of-the-art technique to defend against those attacks. The key challenge to achieving DP in FL lies in the adverse impact of DP noise on model accuracy, particularly for deep learning models with large numbers of parameters. This paper develops a novel differentially-private FL scheme named Fed-SMP that provides a client-level DP guarantee while maintaining high model accuracy. To mitigate the impact of privacy protection on model accuracy, Fed-SMP leverages a new technique called Sparsified Model Perturbation (SMP) where local models are sparsified first before being perturbed by Gaussian noise. We provide a tight end-to-end privacy analysis for Fed-SMP using Renyi DP and prove the convergence of Fed-SMP with both unbiased and biased sparsifications. Extensive experiments on real-world datasets are conducted to demonstrate the effectiveness of Fed-SMP in improving model accuracy with the same DP guarantee and saving communication cost simultaneously.

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。

↑