Client-Side Patching against Backdoor Attacks in Federated Learning

2024/12/13 by Borja Molina Coronado, Molina-Coronado, Borja
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2412.10605

openalex publication_date 2024/12/13 · openalex created_date 2024/12/18 · openalex updated_date 2026/07/28

Abstract

Federated learning is a versatile framework for training models in decentralized environments. However, the trust placed in clients makes federated learning vulnerable to backdoor attacks launched by malicious participants. While many defenses have been proposed, they often fail short when facing heterogeneous data distributions among participating clients. In this paper, we propose a novel defense mechanism for federated learning systems designed to mitigate backdoor attacks on the clients-side. Our approach leverages adversarial learning techniques and model patching to neutralize the impact of backdoor attacks. Through extensive experiments on the MNIST and Fashion-MNIST datasets, we demonstrate that our defense effectively reduces backdoor accuracy, outperforming existing state-of-the-art defenses, such as LFighter, FLAME, and RoseAgg, in i.i.d. and non-i.i.d. scenarios, while maintaining competitive or superior accuracy on clean data.

Related

• On the Vulnerability of Backdoor Defenses for Federated Learning
• Mitigating Backdoor Attacks in Federated Learning
• FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
• Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions
• Mitigating Backdoors in Federated Learning with FLD