计算机工程与应用2026，Vol.62Issue(12)：1-18,18.DOI:10.3778/j.issn.1002-8331.2508-0265
联邦生成对抗网络中的隐私保护技术研究综述
Survey of Privacy-Preserving Techniques in Federated Generative Adversarial Networks
摘要
Abstract
Federated generative adversarial networks(FedGAN)have emerged as a promising privacy-preserving frame-work by integrating generative modeling with federated learning.Unlike traditional centralized GAN,FedGAN enables joint model training without exposing raw data,thereby reducing the risk of privacy leakage.However,due to the intrinsic capability of generative models to reconstruct data distributions,FedGAN remains vulnerable to various privacy attacks such as membership inference and model extraction.This paper provides a comprehensive overview of privacy attack models in FedGAN and surveys the research progress of differential privacy mechanisms within this framework.Specifi-cally,it analyzes the architectural characteristics of FedGAN and the implementation of mainstream privacy-preserving techniques,including differentially private stochastic gradient descent(DPSGD)and Rényi differential privacy(RDP).The paper also briefly introduces the recent applications of knowledge distillation,homomorphic encryption,and secures multi-party computation in the FedGAN context.Finally,this paper summarizes the current challenges and discusses potential future research directions.关键词
联邦学习/生成对抗网络/差分隐私/知识蒸馏Key words
federated learning/generative adversarial network(GAN)/differential privacy/knowledge distillation分类
信息技术与安全科学引用本文复制引用
霍峥,王素贞,张腾飞..联邦生成对抗网络中的隐私保护技术研究综述[J].计算机工程与应用,2026,62(12):1-18,18.基金项目
国家自然科学基金(62002098) （62002098）
河北省自然科学基金(F2025207001) （F2025207001）
河北省省级科技计划项目(246Z0703G) （246Z0703G）
河北省教育厅科学研究项目(QN2022061). （QN2022061）
