One-Shot Backdoor Removal for Federated Learning
- 16 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (23) , 37718-37730
Abstract
Federated learning is a distributed machine learning approach that enables multiple participants to collaboratively train a model without sharing their data, thus preserving privacy. However, the decentralized nature of federated learning also makes it susceptible to backdoor attacks, where malicious participants can embed hidden vulnerabilities within the model. Addressing these threats efficiently and effectively is crucial, especially given the impracticality of iterative and resource-intensive detection methods in federated learning environments. This paper presents a novel framework for one-shot backdoor removal in federated learning. Our approach integrates advanced anomaly detection techniques with a unique model update aggregation strategy, allowing for the identification and neutralization of backdoor influences in a single update cycle without the need for extensive data access or communication between participants. Extensive experiments across various federated architectures and data distributions demonstrate that our method effectively mitigates backdoor threats while maintaining model performance and scalability. This work not only enhances the security of federated models but also contributes to the broader applicability of federated learning in sensitive and critical domains.Keywords
Funding Information
- Postdoctoral Fellowship Program of Cleavage and Polyadenylation Specificity Factor (GZB20230938)
- China Postdoctoral Science Foundation (2023M740246, 2024T171132)
- FDCT under its General Research and Development Subsidy Program Fund, Macau (0038/2022/A)
- NSFC-FDCT under its Joint Scientific Research Project Fund, China, and Macau (0051/2022/AFJ)
This publication has 28 references indexed in Scilit:
- Secure and efficient federated learning via novel multi-party computation and compressed sensingInformation Sciences, 2024
- Proof-of-authority-based secure and efficient aggregation with differential privacy for federated learning in industrial IoTInternet of Things, 2024
- Backdoor attacks and defenses in federated learning: Survey, challenges and future research directionsEngineering Applications of Artificial Intelligence, 2023
- Secure and Efficient Blockchain-Based Federated Learning Approach for VANETsIEEE Internet of Things Journal, 2023
- Multiagent Federated Reinforcement Learning for Resource Allocation in UAV-Enabled Internet of Medical Things NetworksIEEE Internet of Things Journal, 2023
- Communication-Efficient Federated Learning on Non-IID Data Using Two-Step Knowledge DistillationIEEE Internet of Things Journal, 2023
- Defense against backdoor attack in federated learningComputers & Security, 2022
- Joint Training and Resource Allocation Optimization for Federated Learning in UAV SwarmIEEE Internet of Things Journal, 2022
- A Survey on Federated Learning for Resource-Constrained IoT DevicesIEEE Internet of Things Journal, 2021
- D2MIF: A Malicious Model Detection Mechanism for Federated-Learning-Empowered Artificial Intelligence of ThingsIEEE Internet of Things Journal, 2021