Federated Learning (FL) is an emerging paradigm that holds great promise for privacy-preserving machine learning using distributed data. To enhance privacy, FL can be combined with Differential Privacy (DP), which involves adding Gaussian noise to the model weights. However, FL faces a significant challenge in terms of large communication overhead when transmitting these model weights. To address this issue, quantization is commonly employed. Nevertheless, the presence of quantized Gaussian noise introduces complexities in understanding privacy protection. This research paper investigates the impact of quantization on privacy in FL systems. We examine the privacy guarantees of quantized Gaussian mechanisms using R\'enyi Differential Privacy (RDP). By deriving the privacy budget of quantized Gaussian mechanisms, we demonstrate that lower quantization bit levels provide improved privacy protection. To validate our theoretical findings, we employ Membership Inference Attacks (MIA), which gauge the accuracy of privacy leakage. The numerical results align with our theoretical analysis, confirming that quantization can indeed enhance privacy protection. This study not only enhances our understanding of the correlation between privacy and communication in FL but also underscores the advantages of quantization in preserving privacy.

翻译：联邦学习（FL）是一种新兴范式，在利用分布式数据实现隐私保护机器学习方面具有巨大潜力。为增强隐私保护，FL可与差分隐私（DP）结合，具体方法是在模型权重中添加高斯噪声。然而，FL在传输这些模型权重时面临通信开销大的重大挑战。为解决这一问题，常采用量化技术。但量化高斯噪声的存在增加了隐私保护理解的复杂性。本研究论文探讨了FL系统中量化对隐私的影响。我们运用Rényi差分隐私（RDP）分析了量化高斯机制的隐私保证。通过推导量化高斯机制的隐私预算，表明较低的量化比特级可提供更好的隐私保护。为验证理论发现，我们采用成员推理攻击（MIA）来衡量隐私泄露的准确性。数值结果与理论分析一致，证实量化确实能增强隐私保护。这项研究不仅加深了我们对FL中隐私与通信之间关联的理解，还凸显了量化在保护隐私方面的优势。