GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learning

2024/05/31 by Xiaoyun Gan, Gan, Xiaoyun, Shanyu Gan +5
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Cryptography and Data Security #Cryptography and Security (cs.CR) #Distributed #FOS: Computer and information sciences #Parallel #Privacy-Preserving Technologies in Data #and Cluster Computing (cs.DC)

paper · pdf · doi:10.48550/arxiv.2405.20727

openalex publication_date 2024/05/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

With heightened awareness of data privacy protection, Federated Learning (FL) has attracted widespread attention as a privacy-preserving distributed machine learning method. However, the distributed nature of federated learning also provides opportunities for backdoor attacks, where attackers can guide the model to produce incorrect predictions without affecting the global model training process. This paper introduces a novel defense mechanism against backdoor attacks in federated learning, named GANcrop. This approach leverages contrastive learning to deeply explore the disparities between malicious and benign models for attack identification, followed by the utilization of Generative Adversarial Networks (GAN) to recover backdoor triggers and implement targeted mitigation strategies. Experimental findings demonstrate that GANcrop effectively safeguards against backdoor attacks, particularly in non-IID scenarios, while maintaining satisfactory model accuracy, showcasing its remarkable defensive efficacy and practical utility.

Related

• FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
• Mingling with the Good to Backdoor Federated Learning
• Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions
• On the Vulnerability of Backdoor Defenses for Federated Learning
• How To Backdoor Federated Learning