Nosy Layers, Noisy Fixes: 使用可解释AI 应对联邦学习中的DRAs

联邦学习（Federated Learning, FL）已成为一种在保持客户端数据去中心化和私有的前提下进行协作模型训练的强大范式。然而，它 vulnerable to Data Reconstruction Attacks（DRAs） such as "LoKI" and "Robbing the Fed"，其中由服务器发送给客户端的恶意模型可重建敏感用户数据。为对抗此类攻击，我们引入DRArmor，一种 novel defense mechanism that integrates Explainable AI with targeted detection and mitigation strategies for DRA。 Unlike existing defenses that focus on the entire model, DRArmor identifies and addresses the root cause（即发送带有恶意意图的梯度的模型中的恶意层） by analyzing their contribution to the output and detecting inconsistencies in gradient values。 Once these malicious layers are identified, DRArmor applies defense techniques such as noise injection, pixelation, and pruning to these layers rather than the whole model, minimizing the attack surface and preserving client data privacy。我们在200客户端 FL setup 中评估了DRArmor针对高级LoKI攻击的性能，包括MNIST、CIFAR-10、CIFAR-100和ImageNet等 diverse datasets。Our results demonstrate DRArmor's effectiveness in mitigating data leakage, achieving high True Positive and True Negative Rates of 0.910 and 0.890, respectively。Additionally, DRArmor maintains an average accuracy of 87%, effectively protecting client privacy without compromising model performance。Compared to existing defense mechanisms, DRArmor reduces the data leakage rate by 62.5% with datasets containing 500 samples per client。