A Reputation-Aware Defense Framework for Strategic Behaviors in Federated Learning
Open Access
Abstract
Federated Learning (FL) enables privacy-preserving model training across distributed clients. However, its reliance on voluntary client participation makes it vulnerable to strategic behaviors—actions that are not overtly malicious but significantly impair model convergence and fairness. Existing defense methods primarily focus on explicit attacks, overlooking the challenges posed by economically motivated “pseudo-honest” clients. To address this gap, we propose a Reputation-Aware Defense Framework to mitigate strategic behaviors in FL. This framework introduces a multi-dimensional dynamic reputation model that evaluates client behaviors based on gradient alignment, participation consistency, and update stability. The resulting reputation scores are incorporated into both aggregation and incentive mechanisms, forming a behavior-feedback loop that rewards honest participation and penalizes opportunistic strategies. We theoretically prove the convergence of reputation scores, the suppression of low-quality updates in aggregation, and the emergence of honest participation as a Nash equilibrium under the incentive mechanism. Experiments on datasets such as CIFAR-10, FEMNIST, MIMIC-III demonstrate that our approach significantly outperforms baseline methods in accuracy, fairness, and robustness, even when up to 60% of clients act strategically. This study bridges trust modeling and robust optimization in FL, offering a secure foundation for federated systems operating in open and incentive-driven environments.Keywords
Funding Information
- Hainan Provincial Natural Science Foundation of China (823QN229, 625MS046, 624QN230, JP24KF0065)
- JSPS KAKENHI (823QN229, 625MS046, 624QN230, JP24KF0065)
This publication has 46 references indexed in Scilit:
- Multi-round decentralized dataset distillation with federated learning for Low Earth Orbit satellite communicationFuture Generation Computer Systems, 2024
- A survey on federated learning: challenges and applicationsInternational Journal of Machine Learning and Cybernetics, 2022
- Federated Learning for Internet of Things: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2021
- A survey on security and privacy of federated learningFuture Generation Computer Systems, 2021
- Blockchain-Based Federated Learning for Device Failure Detection in Industrial IoTIEEE Internet of Things Journal, 2020
- The future of digital health with federated learningnpj Digital Medicine, 2020
- Federated Learning in Mobile Edge Networks: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2020
- Hierarchical Incentive Mechanism Design for Federated Machine Learning in Mobile NetworksIEEE Internet of Things Journal, 2020
- A Learning-Based Incentive Mechanism for Federated LearningIEEE Internet of Things Journal, 2020
- Incentive Mechanism for Reliable Federated Learning: A Joint Optimization Approach to Combining Reputation and Contract TheoryIEEE Internet of Things Journal, 2019