paper-with-me

Papers

Cross-Context Backdoor Attacks against Graph Prompt Learning

2024-05-28 · Xiaoting Lyu, Yufei Han, Wei Wang, Hangwei Qian, Ivor Tsang, Xiangliang Zhang

Graph Prompt Learning (GPL) bridges significant disparities between pretraining and downstream applications to alleviate the knowledge transfer bottleneck in real-world graph learning. While GPL offers superior effectiveness in graph knowledge transfer and computational efficiency, the security risks posed by backdoor poisoning effects embedded in pretrained models remain largely unexplored. Our study provides a comprehensive analysis of GPL's vulnerability to backdoor attacks. We introduce \textit{CrossBA}, the first cross-context backdoor attack against GPL, which manipulates only the pretraining phase without requiring knowledge of downstream applications. Our investigation reveals both theoretically and empirically that tuning trigger graphs, combined with prompt transformations, can seamlessly transfer the backdoor threat from pretrained encoders to downstream applications. Through extensive experiments involving 3 representative GPL methods across 5 distinct cross-context scenarios and 5 benchmark datasets of node and graph classification tasks, we demonstrate that \textit{CrossBA} consistently achieves high attack success rates while preserving the functionality of downstream applications over clean input. We also explore potential countermeasures against \textit{CrossBA} and conclude that current defenses are insufficient to mitigate \textit{CrossBA}. Our study highlights the persistent backdoor threats to GPL systems, raising trustworthiness concerns in the practices of GPL techniques.

📄 PDF Abstract BibTeX arXiv:2405.17984

Code (1)

xtLyu/CrossBA 공식 구현 pytorch

Tasks

Backdoor AttackComputational EfficiencyGraph ClassificationGraph LearningPrompt LearningTransfer Learning

Similar Papers 제목 키워드 기반

On the Robustness of Graph Reduction Against GNN Backdoor

2024-07-02 · Yuxuan Zhu, Michael Mandulak, Kerui Wu, George Slota 외

Graph Neural Networks (GNNs) are gaining popularity across various domains due to their effectiveness in learning graph-structured data. Nevertheless, they have been shown to be susceptible to backdoor poisoning attacks,…

Computational EfficiencyData Poisoning

DMGNN: Detecting and Mitigating Backdoor Attacks in Graph Neural Networks

2024-10-18 · Hao Sui, Bing Chen, Jiale Zhang, Chengcheng Zhu 외

Recent studies have revealed that GNNs are highly susceptible to multiple adversarial attacks. Among these, graph backdoor attacks pose one of the most prominent threats, where attackers cause models to misclassify by le…

counterfactualCounterfactual Explanation

Backdoor Attacks to Graph Neural Networks

2020-06-19 · Zaixi Zhang, Jinyuan Jia, Binghui Wang, Neil Zhenqiang Gong

In this work, we propose the first backdoor attack to graph neural networks (GNN). Specifically, we propose a \emph{subgraph based backdoor attack} to GNN for graph classification. In our backdoor attack, a GNN classifie…

Backdoor AttackGeneral ClassificationGraph ClassificationNode Classification

Robustness Inspired Graph Backdoor Defense

2024-06-14 · Zhiwei Zhang, Minhua Lin, Junjie Xu, Zongyu Wu 외

Graph Neural Networks (GNNs) have achieved promising results in tasks such as node classification and graph classification. However, recent studies reveal that GNNs are vulnerable to backdoor attacks, posing a significan…

backdoor defenseGraph ClassificationNode Classification

Effective backdoor attack on graph neural networks in link prediction tasks

2024-01-05 · Jiazhu Dai, Haoyu Sun

Graph Neural Networks (GNNs) are a class of deep learning models capable of processing graph-structured data, and they have demonstrated significant performance in a variety of real-world applications. Recent studies hav…

Backdoor AttackGraph ClassificationLink PredictionNode Classification