通过PPA和极小极大博弈论缓解联邦学习中的后门攻击
Mitigating Backdoor Attacks in Federated Learning Using PPA and MiniMax Game Theory
AI总结：
本文提出FedBBA方法，结合声誉系统、激励机制和博弈论模型，通过投影追求分析动态识别并减少恶意客户端对全局模型的影响，实验表明其在多个攻击场景中显著降低后门攻击成功率。
摘要：
联邦学习（FL）因其能在保护隐私的同时利用大量分散数据而得到广泛应用。然而，联邦学习面临诸多挑战，直接影响其生成的全局模型的准确性和完整性。恶意客户端通过在本地模型中注入后门数据来破坏全局模型，旨在使全局模型在推理时做出错误预测。为缓解此类恶意行为，我们提出FedBBA（联邦后门和行为分析）。该方法旨在削弱恶意客户端对最终准确率的影响，创建更稳健的联邦学习环境。我们的方法通过结合（1）声誉系统评估和跟踪客户端行为，（2）激励机制奖励诚实参与并惩罚恶意行为，以及（3）具有投影追求分析（PPA）的博弈论模型，动态识别并最小化恶意客户端对全局模型的影响。在德国交通标志识别基准（GTSRB）和比利时交通标志分类（BTSC）数据集上的广泛模拟表明，FedBBA在各种攻击场景中将后门攻击成功率降至约1.1%至11%，显著优于RDFL和RoPE等现有防御方法，后者在23%至76%之间，同时保持高正常任务准确率（约95%至98%）。
英文摘要：
Federated Learning (FL) is witnessing wider adoption due to its ability to benefit from large amounts of scattered data while preserving privacy. However, despite its advantages, federated learning suffers from several setbacks that directly impact the accuracy, and the integrity of the global model it produces. One of these setbacks is the presence of malicious clients who actively try to harm the global model by injecting backdoor data into their local models while trying to evade detection. The objective of such clients is to trick the global model into making false predictions during inference, thereby compromising the integrity and trustworthiness of the global model on which honest stakeholders rely. To mitigate such mischievous behavior, we propose FedBBA (Federated Backdoor and Behavior Analysis). The proposed model aims to dampen the effect of such clients on the final accuracy, creating more resilient federated learning environments. We engineer our approach through the combination of (1) a reputation system to evaluate and track client behavior, (2) an incentive mechanism to reward honest participation and penalize malicious behavior, and (3) game theoretical models with projection pursuit analysis (PPA) to dynamically identify and minimize the impact of malicious clients on the global model. Extensive simulations on the German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign Classification (BTSC) datasets demonstrate that FedBBA reduces the backdoor attack success rate to approximately 1.1%--11% across various attack scenarios, significantly outperforming state-of-the-art defenses like RDFL and RoPE, which yielded attack success rates between 23% and 76%, while maintaining high normal task accuracy (~95%--98%).
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。
