动态调整隐私预算和梯度裁剪，提升联邦学习的隐私与性能平衡。
Evaluation of Differential Privacy Mechanisms on Federated Learning
- 基于自适应隐私预算与动态梯度裁剪，减少收敛后噪声过载。
- 在200轮训练中，保持模型准确率的同时实现更强隐私保护。
- 适合关注联邦学习隐私机制优化的研究者与工业应用开发者。
联邦学习是在不共享原始数据的前提下，在多个客户端间进行分布式模型训练。尽管数据隐私技术不断进步，仍存在风险。差分隐私（DP）通过向模型更新添加噪声来保护敏感数据，通常由固定隐私预算控制。然而，该方法在模型收敛后可能引入过多噪声，损害性能。为此，本文采用拉普拉斯与高斯机制，结合自适应隐私预算，并在高斯机制中引入自适应裁剪策略，使模型梯度动态更新而非使用固定敏感度。实验在200轮训练下，针对不同隐私预算、独立同分布（IID）与非独立同分布（non-IID）数据集、每轮选取不同数量客户端进行了评估。结果表明，自适应隐私预算与自适应裁剪有助于在保障隐私的同时维持模型精度。
原文摘要 · Abstract (English)
Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding noise to model updates, usually controlled by a fixed privacy budget. However, this approach can introduce excessive noise, particularly when the model converges, which compromises performance. To address this problem, adaptive privacy budgets have been investigated as a potential solution. This work implements DP methods using Laplace and Gaussian mechanisms with an adaptive privacy budget, extending the SelecEval simulator. We introduce an adaptive clipping approach in the Gaussian mechanism, ensuring that gradients of the model are dynamically updated rather than using a fixed sensitivity. We conduct extensive experiments with various privacy budgets, IID and non-IID datasets, and different numbers of selected clients per round. While our experiments were limited to 200 training rounds, the results suggest that adaptive privacy budgets and adaptive clipping can help maintain model accuracy while preserving privacy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。