arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.06337cs.NIeess.SP
收藏

差分私有AirComp联邦学习与功率自适应利用接收机噪声

Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noise

Yusuke Koda, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura

摘要:

基于空中计算(AirComp)的联邦学习(FL)通过利用同时的同信道传输和所产生的波形叠加来实现低延迟上传和机器学习模型的聚合。本研究旨在实现安全的AirComp-based FL对各种隐私攻击,恶意的中央服务器推断客户端的隐私数据从聚合的全球模型。为此,在这项研究中,差分私有AirComp-based FL的设计,其中的关键思想是利用接收机噪声扰动注入到聚合的全球模型固有的,从而防止客户端的私人数据的推断。然而,固有的接收机噪声的方差通常是不可控的,这使得注入适当的噪声扰动以实现期望的隐私级别的过程相当具有挑战性。因此,本研究设计跨客户端的发射功率控制,其中接收信号电平被有意地调整以有效地控制噪声扰动水平,从而实现期望的隐私水平。据观察,较高的隐私级别需要较低的发射功率,这表明隐私级别和信噪比(SNR)之间的权衡。为了更全面地理解这种权衡,推导出SNR(相对于隐私级别)的封闭形式表达式,并分析证明了这种权衡。分析结果还表明,在可配置的参数,参与的客户端的数量是一个关键的参数,提高了接收的信噪比下,上述权衡。通过数值计算验证了分析结果。

英文摘要:

Over-the-air computation (AirComp)-based federated learning (FL) enables low-latency uploads and the aggregation of machine learning models by exploiting simultaneous co-channel transmission and the resultant waveform superposition. This study aims at realizing secure AirComp-based FL against various privacy attacks where malicious central servers infer clients' private data from aggregated global models. To this end, a differentially private AirComp-based FL is designed in this study, where the key idea is to harness receiver noise perturbation injected to aggregated global models inherently, thereby preventing the inference of clients' private data. However, the variance of the inherent receiver noise is often uncontrollable, which renders the process of injecting an appropriate noise perturbation to achieve a desired privacy level quite challenging. Hence, this study designs transmit power control across clients, wherein the received signal level is adjusted intentionally to control the noise perturbation levels effectively, thereby achieving the desired privacy level. It is observed that a higher privacy level requires lower transmit power, which indicates the tradeoff between the privacy level and signal-to-noise ratio (SNR). To understand this tradeoff more fully, the closed-form expressions of SNR (with respect to the privacy level) are derived, and the tradeoff is analytically demonstrated. The analytical results also demonstrate that among the configurable parameters, the number of participating clients is a key parameter that enhances the received SNR under the aforementioned tradeoff. The analytical results are validated through numerical evaluations.

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。

↑