Universal Graph Backdoor Defense: A Feature-based Homophily Perspective

Computer Science > Cryptography and Security [Submitted on 16 May 2026] Universal Graph Backdoor Defense: A Feature-based Homophily Perspective Mengting Pan, Fan Li, Chen Chen, Xiaoyang Wang Graph neural networks (GNNs) have achieved remarkable success in relational learning. However, their vulnerability to graph backdoor attacks (GBAs) poses a significant barrier to broader adoption in high-stakes applications. Despite recent advances in graph backdoor defense (GBD), existing methods primarily focus on subgraph-based GBAs, relying on the assumption that poisoned target nodes are explicitly connected to subgraph triggers. Our empirical results reveal that such structure-centric approaches fail to defend against emerging feature-based GBAs that preserve graph topology. Therefore, in this paper, we study a novel problem of universal graph backdoor defense. First, we investigate the shared effects of both attack types from a feature-based homophily perspective, which characterizes local feature consistency between nodes and their neighborhoods. Thorough theoretical and empirical analyses demonstrate that, regardless of trigger mechanisms, backdoors induced by GBAs exhibit lower feature-based homophily than clean nodes, indicating a discrepancy in local feature similarity. Motivated by this insight, we propose to leverage node-level local feature consistency, modeled by a neighbor-aware reconstruction loss, to distinguish backdoors from clean nodes. Then, a robust training strategy is developed to eliminate trigger effects while reducing noise induced by detection uncertainty. Extensive experiments demonstrate that our framework significantly degrades the attack success rate and maintains competitive clean accuracy under both subgraph-based and feature-based attacks. Comments: 17 pages, 6 figures Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2605.16815 [cs.CR]   (or arXiv:2605.16815v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.16815 Focus to learn more Submission history From: Mengting Pan [view email] [v1] Sat, 16 May 2026 05:15:36 UTC (391 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)