arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.05907eess.SP
收藏

通过客户端驱动的功率平衡提升隐私的空中联邦学习

Privacy-Enhanced Over-the-Air Federated Learning via Client-Driven Power Balancing

Seoul National University (SNU)(首尔大学);Sungkyunkwan University(成均馆大学)

Bumjun Kim, Hyowoon Seo, Wan Choi

AI总结:

本文提出客户端驱动功率平衡策略,通过独立调整传输功率提升OTA-FL的隐私保护与学习效率,实验表明其在模型准确性和隐私保障方面优于传统方法。

摘要:

本文介绍了一种新型隐私增强的空中联邦学习(OTA-FL)框架,采用客户端驱动的功率平衡(CDPB)技术以解决OTA-FL系统中的隐私问题。现有研究中,服务器根据每个客户端持续传输的信道状态信息(CSI)确定功率平衡,并在每个全局迭代中集中满足隐私要求,这可能随着学习过程的延长而增加隐私暴露风险。为缓解这些风险,我们提出两种CDPB策略——CDPB-n(噪声)和CDPB-i(空闲),允许客户端独立调整传输功率,不共享CSI。CDPB-n在条件差时传输噪声,而CDPB-i在条件改善前暂停传输。为进一步增强隐私和学习效率,我们展示了一种混合策略CDPB-mixed,结合CDPB-n和CDPB-i。实验结果表明,CDPB在模型准确性和隐私保障方面优于传统方法,为资源受限环境下的OTA-FL提供了实用解决方案。

英文摘要:

This paper introduces a novel privacy-enhanced over-the-air Federated Learning (OTA-FL) framework using client-driven power balancing (CDPB) to address privacy concerns in OTA-FL systems. In recent studies, a server determines the power balancing based on the continuous transmission of channel state information (CSI) from each client. Furthermore, they concentrate on fulfilling privacy requirements in every global iteration, which can heighten the risk of privacy exposure as the learning process extends. To mitigate these risks, we propose two CDPB strategies -- CDPB-n (noisy) and CDPB-i (idle) -- allowing clients to adjust transmission power independently, without sharing CSI. CDPB-n transmits noise during poor conditions, while CDPB-i pauses transmission until conditions improve. To further enhance privacy and learning efficiency, we show a mixed strategy, CDPB-mixed, which combines CDPB-n and CDPB-i. Our experimental results show that CDPB outperforms traditional approaches in terms of model accuracy and privacy guarantees, providing a practical solution for enhancing OTA-FL in resource-constrained environments.

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。

↑