Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool
Jiangtong Li, Dungy Liu, Dawei Cheng, Changchun Jiang

TL;DR
This paper introduces a novel multi-category graph backdoor attack method using subgraph triggers, which is more effective and less noticeable than previous single-category approaches, demonstrating success across various datasets and defenses.
Contribution
The paper proposes a category-aware subgraph trigger pool and a 'select then attach' strategy for multi-category graph backdoor attacks, addressing limitations of prior adaptive trigger generators.
Findings
Effective multi-category backdoor attacks demonstrated across multiple datasets.
The method outperforms existing single-category approaches in attack success.
Attacks remain unnoticeable to defense strategies.
Abstract
\textbf{G}raph \textbf{N}eural \textbf{N}etworks~(GNNs) have achieved significant success in various real-world applications, including social networks, finance systems, and traffic management. Recent researches highlight their vulnerability to backdoor attacks in node classification, where GNNs trained on a poisoned graph misclassify a test node only when specific triggers are attached. These studies typically focus on single attack categories and use adaptive trigger generators to create node-specific triggers. However, adaptive trigger generators typically have a simple structure, limited parameters, and lack category-aware graph knowledge, which makes them struggle to handle backdoor attacks across multiple categories as the number of target categories increases. We address this gap by proposing a novel approach for \textbf{E}ffective and \textbf{U}nnoticeable…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Graph Neural Networks · Advanced Malware Detection Techniques · Complex Network Analysis Techniques
