HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning

Momin Ahmad Khan, Yasra Chandio, Fatima M. Anwar

Keywords: Federated Learning, Knowledge Distillation, Poisoning Attacks

TL;DR: We show that Knowledge Distillation amplifies model poisoning attacks in FL, and design our algorithm HYDRA-FL to mitigate attack ampification.

Abstract:

Data heterogeneity among Federated Learning (FL) users poses a significant challenge, resulting in reduced global model performance. The community has designed various techniques to tackle this issue, among which Knowledge Distillation (KD)-based techniques are common.
While these techniques effectively improve performance under high heterogeneity, they inadvertently cause higher accuracy degradation under model poisoning attacks (known as \emph{attack amplification}). This paper presents a case study to reveal this critical vulnerability in KD-based FL systems. We show why KD causes this issue through empirical evidence and use it as motivation to design a hybrid distillation technique. We introduce a novel algorithm, Hybrid Knowledge Distillation for Robust and Accurate FL (HYDRA-FL), which reduces the impact of attacks in attack scenarios by offloading some of the KD loss to a shallow layer via an auxiliary classifier. We model HYDRA-FL as a generic framework and adapt it to two KD-based FL algorithms, FedNTD and MOON. Using these two as case studies, we demonstrate that our technique outperforms baselines in attack settings while maintaining comparable performance in benign settings.

Primary Area: Other (please use sparingly, only use the keyword field for more details)

Submission Number: 12300