arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.12704cs.AI
收藏

针对图卷积网络的仅污染标签的干净图后门攻击

A Clean-graph Backdoor Attack against Graph Convolutional Networks with Poisoned Label Only

Jiazhu Dai, Haoyu Sun

AI总结:

本文提出一种针对图卷积网络的干净图后门攻击(CBAG),仅通过污染训练标签注入后门,无需修改训练样本,实现了99%的攻击成功率且不影响模型在良性样本上的性能。

摘要:

图卷积网络(GCNs)在处理各种图结构(如节点分类、图分类等任务)中表现出优异的性能。然而,近期研究表明,GCNs容易受到一种称为后门攻击的新型威胁。然而,目前图领域所有现有的后门攻击都需要修改训练样本以完成后门注入,这在许多现实场景中可能不切实际,因为对手无法修改训练样本,并且可能导致后门攻击容易被检测。为了探索GCNs的后门脆弱性,并创造一种更实用且隐蔽的后门攻击方法,本文提出了一种针对GCNs的干净图后门攻击(CBAG),用于节点分类任务,该攻击仅污染训练标签,不对训练样本进行任何修改,揭示了GCNs存在这一安全漏洞。具体而言,CBAG设计了一种新的触发器探索方法,以找到重要的特征维度作为触发模式,从而提高攻击性能。通过污染训练标签,将隐藏的后门注入GCNs模型。实验结果表明,我们的干净图后门攻击能够达到99%的攻击成功率,同时保持GCNs模型在良性样本上的功能。

英文摘要:

Graph Convolutional Networks (GCNs) have shown excellent performance in dealing with various graph structures such as node classification, graph classification and other tasks. However,recent studies have shown that GCNs are vulnerable to a novel threat known as backdoor attacks. However, all existing backdoor attacks in the graph domain require modifying the training samples to accomplish the backdoor injection, which may not be practical in many realistic scenarios where adversaries have no access to modify the training samples and may leads to the backdoor attack being detected easily. In order to explore the backdoor vulnerability of GCNs and create a more practical and stealthy backdoor attack method, this paper proposes a clean-graph backdoor attack against GCNs (CBAG) in the node classification task,which only poisons the training labels without any modification to the training samples, revealing that GCNs have this security vulnerability. Specifically, CBAG designs a new trigger exploration method to find important feature dimensions as the trigger patterns to improve the attack performance. By poisoning the training labels, a hidden backdoor is injected into the GCNs model. Experimental results show that our clean graph backdoor can achieve 99% attack success rate while maintaining the functionality of the GCNs model on benign samples.

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。

↑