A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning
This work is significant for federated learning participants and system designers who need to ensure fair compensation for contributions and protect against malicious actors, representing an incremental improvement in FL security and fairness.
This paper addresses collaborative fairness and adversarial robustness in federated learning by proposing a Robust and Fair Federated Learning (RFFL) framework. RFFL uses a reputation mechanism based on gradient similarity to identify and remove non-contributing or malicious participants, achieving high fairness and robustness without auxiliary datasets.
Federated learning (FL) is an emerging practical framework for effective and scalable machine learning among multiple participants, such as end users, organizations and companies. However, most existing FL or distributed learning frameworks have not well addressed two important issues together: collaborative fairness and adversarial robustness (e.g. free-riders and malicious participants). In conventional FL, all participants receive the global model (equal rewards), which might be unfair to the high-contributing participants. Furthermore, due to the lack of a safeguard mechanism, free-riders or malicious adversaries could game the system to access the global model for free or to sabotage it. In this paper, we propose a novel Robust and Fair Federated Learning (RFFL) framework to achieve collaborative fairness and adversarial robustness simultaneously via a reputation mechanism. RFFL maintains a reputation for each participant by examining their contributions via their uploaded gradients (using vector similarity) and thus identifies non-contributing or malicious participants to be removed. Our approach differentiates itself by not requiring any auxiliary/validation dataset. Extensive experiments on benchmark datasets show that RFFL can achieve high fairness and is very robust to different types of adversaries while achieving competitive predictive accuracy.