Byzantine-Robust Aggregation for Securing Decentralized Federated Learning
This addresses the problem of securing decentralized federated learning against Byzantine attacks, offering a robust solution for scalable and resilient distributed AI systems, though it is incremental as it builds on existing Byzantine-robust methods.
The paper tackles the security challenge of Byzantine attacks in Decentralized Federated Learning by proposing a novel aggregation algorithm called WFAgg, which outperforms state-of-the-art centralized schemes in maintaining model accuracy and convergence under various attack scenarios.
Federated Learning (FL) emerges as a distributed machine learning approach that addresses privacy concerns by training AI models locally on devices. Decentralized Federated Learning (DFL) extends the FL paradigm by eliminating the central server, thereby enhancing scalability and robustness through the avoidance of a single point of failure. However, DFL faces significant challenges in optimizing security, as most Byzantine-robust algorithms proposed in the literature are designed for centralized scenarios. In this paper, we present a novel Byzantine-robust aggregation algorithm to enhance the security of Decentralized Federated Learning environments, coined WFAgg. This proposal handles the adverse conditions and strength robustness of dynamic decentralized topologies at the same time by employing multiple filters to identify and mitigate Byzantine attacks. Experimental results demonstrate the effectiveness of the proposed algorithm in maintaining model accuracy and convergence in the presence of various Byzantine attack scenarios, outperforming state-of-the-art centralized Byzantine-robust aggregation schemes (such as Multi-Krum or Clustering). These algorithms are evaluated on an IID image classification problem in both centralized and decentralized scenarios.