A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning

2020/11/20 by Xinyi Xu, Lingjuan Lyu, Xu, Xinyi +1 · 4 citations
Computer Science · Mathematics · Social Sciences · #Adversarial Robustness in Machine Learning #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Privacy-Preserving Technologies in Data #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.2011.10464

Accepted as Oral presentation at International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2021 (FL-ICML'21)

openalex publication_date 2020/11/20 · arxiv created 2021/07/27 · arxiv updated 2021/07/28 · openalex created_date 2021/08/02 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• On the difficulty of training Recurrent Neural Networks
• Gradient-based learning applied to document recognition
• Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
• Local SGD Converges Fast and Communicates Little
• Mitigating Sybils in Federated Learning Poisoning
• Differentially Private Fair Learning
• Convolutional Neural Networks for Sentence Classification
• Advances and Open Problems in Federated Learning
• Threats to Federated Learning: A Survey
• Federated Model Distillation with Noise-Free Differential Privacy
• ByGARS: Byzantine SGD with Arbitrary Number of Attackers
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Adaptive Federated Learning Defences via Trust-Aware Deep Q-Networks
• Fairness in Federated Learning: Trends, Challenges, and Opportunities
• FAIRVAR: Fair Federated Learning via Variance Regularization
• Bant: Byzantine Antidote via Trial Function and Trust Scores

Related

• Collaborative Fairness in Federated Learning
• MURIM: Multidimensional Reputation-based Incentive Mechanism for Federated Learning
• Towards Trustworthy Federated Learning
• Towards Multi-Objective Statistically Fair Federated Learning
• FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning