Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attacks
This addresses security vulnerabilities in Federated Learning for privacy-preserving collaborative training, though it appears incremental as it builds on existing defence mechanisms.
The paper tackles the problem of backdoor attacks in Federated Learning by proposing Robust Knowledge Distillation (RKD), which effectively mitigates threats while maintaining high model performance, outperforming state-of-the-art methods across various scenarios.
Federated Learning (FL) enables collaborative model training across multiple devices while preserving data privacy. However, it remains susceptible to backdoor attacks, where malicious participants can compromise the global model. Existing defence methods are limited by strict assumptions on data heterogeneity (Non-Independent and Identically Distributed data) and the proportion of malicious clients, reducing their practicality and effectiveness. To overcome these limitations, we propose Robust Knowledge Distillation (RKD), a novel defence mechanism that enhances model integrity without relying on restrictive assumptions. RKD integrates clustering and model selection techniques to identify and filter out malicious updates, forming a reliable ensemble of models. It then employs knowledge distillation to transfer the collective insights from this ensemble to a global model. Extensive evaluations demonstrate that RKD effectively mitigates backdoor threats while maintaining high model performance, outperforming current state-of-the-art defence methods across various scenarios.