HPE: 生成正纠缠用于联邦自监督学习中的后门攻击
HPE: Hallucinated Positive Entanglement for Backdoor Attacks in Federated Self-Supervised Learning
AI总结：
HPE通过生成正纠缠技术提升联邦自监督学习中后门攻击的效率和鲁棒性。
摘要：
联邦自监督学习（FSSL）能够在不共享原始未标记数据的情况下实现自监督表示模型的协同训练。尽管它为隐私保护学习提供了关键范式，但其安全性仍容易受到后门攻击的威胁，其中恶意客户端通过操纵本地训练来注入目标后门。然而，现有FSSL攻击方法往往存在对受污染样本利用低、转移性有限和持久性弱的问题。为了解决这些限制，我们提出了一种新的FSSL后门攻击方法，即生成正纠缠（HPE）。HPE首先使用基于生成的正样本进行增强，以增强编码器对后门特征的嵌入。然后引入特征纠缠，以在表示空间中强制触发器和后门样本之间的紧密绑定。最后，选择性参数污染和基于接近度的更新将受污染模型限制在全局模型的附近，从而增强其稳定性和持久性。在多个FSSL场景和数据集上的实验结果表明，HPE在性能上显著优于现有后门攻击方法，并且在各种防御机制下表现出强大的鲁棒性。
英文摘要：
Federated self-supervised learning (FSSL) enables collaborative training of self-supervised representation models without sharing raw unlabeled data. While it serves as a crucial paradigm for privacy-preserving learning, its security remains vulnerable to backdoor attacks, where malicious clients manipulate local training to inject targeted backdoors. Existing FSSL attack methods, however, often suffer from low utilization of poisoned samples, limited transferability, and weak persistence. To address these limitations, we propose a new backdoor attack method for FSSL, namely Hallucinated Positive Entanglement (HPE). HPE first employs hallucination-based augmentation using synthetic positive samples to enhance the encoder's embedding of backdoor features. It then introduces feature entanglement to enforce tight binding between triggers and backdoor samples in the representation space. Finally, selective parameter poisoning and proximity-aware updates constrain the poisoned model within the vicinity of the global model, enhancing its stability and persistence. Experimental results on several FSSL scenarios and datasets show that HPE significantly outperforms existing backdoor attack methods in performance and exhibits strong robustness under various defense mechanisms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
