Detect \& Score: Privacy-Preserving Misbehaviour Detection and Contribution Evaluation in Federated Learning

TL;DR

This paper presents a combined approach to enhance privacy-preserving federated learning by improving misbehaviour detection and contribution evaluation, addressing limitations of existing methods QI and FedGT.

Contribution

It introduces a novel method that integrates QI and FedGT to achieve both accurate contribution evaluation and robust misbehaviour detection in federated learning.

Findings

Superior performance over individual methods in experiments

Enhanced accuracy in contribution evaluation

Improved misbehaviour detection robustness

Abstract

Federated learning with secure aggregation enables private and collaborative learning from decentralised data without leaking sensitive client information. However, secure aggregation also complicates the detection of malicious client behaviour and the evaluation of individual client contributions to the learning. To address these challenges, QI (Pejo et al.) and FedGT (Xhemrishi et al.) were proposed for contribution evaluation (CE) and misbehaviour detection (MD), respectively. QI, however, lacks adequate MD accuracy due to its reliance on the random selection of clients in each training round, while FedGT lacks the CE ability. In this work, we combine the strengths of QI and FedGT to achieve both robust MD and accurate CE. Our experiments demonstrate superior performance compared to using either method independently.