作者：Lei Shi, Han Wu, Xu Ding, Hao Xu, Sinan Pan发表刊物：IEEE Internet of Things Journal

年份：November 2025

摘要：Clustered Federated Learning (CFL) has emerged as an effective solution to address data heterogeneity in traditional Federated Learning (FL). However, the intrinsic cluster-based structure of CFL introduces new privacy risks, making it more vulnerable to client-level inference attacks. In this paper, we propose a novel client-level data reconstruction attack based on Conditional Generative Adversarial Networks (cGANs), which exploits intra-cluster similarities to enhance the quality of reconstructed private data. Unlike prior works, our attack requires only partial access to a victim’s model updates through passive eavesdropping, thereby reflecting a more realistic threat model in decentralized and resource-constrained environments such as the Internet of Things (IoT). To mitigate this threat, we develop a lightweight and adaptive defense mechanism grounded in Local Differential Privacy (LDP). Our design incorporates dynamic privacy budget decay, selective layer-wise noise injection, and real-time similarity-guided adaptation. This approach achieves a favorable privacy-utility trade-off while explicitly addressing the computational, communication, and latency constraints inherent in IoT environments. Experimental results demonstrate that our proposed attack improves reconstruction similarity by up to 20% compared with existing baselines, while the defense reduces attack success rate by 27.2% with only a 3.3% accuracy drop. Moreover, it significantly lowers computational cost—reducing FLOPs by 42.7%, memory usage by 23.4%, and DP noise processing time by 45.5%—without introducing additional communication overhead. These findings highlight the underestimated privacy vulnerabilities in CFL and underscore the necessity of efficient, context-aware defense strategies.

参考文献拷贝字段：Lei Shi, Han Wu, Xu Ding, Hao Xu, Sinan Pan. A Client-level Conditonal Generative Adversarial Network-based Data Reconstruction Attack and its Defense in Clustered Federated Learning Scenario [J]. IEEE Internet of Things Journal. 2025.  DOI: https://doi.org/10.1109/JIOT.2025.3637061