{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:56:24Z","timestamp":1781301384020,"version":"3.54.1"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061146002"],"award-info":[{"award-number":["62061146002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206238"],"award-info":[{"award-number":["62206238"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176122"],"award-info":[{"award-number":["62176122"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012659","name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M732985"],"award-info":[{"award-number":["2023M732985"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113693","type":"journal-article","created":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T16:25:58Z","timestamp":1776011158000},"page":"113693","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Explanation-guided backdoor defense for ID and OOD attacks in graph neural networks"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8527-1238","authenticated-orcid":false,"given":"Hao","family":"Sui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2863-5441","authenticated-orcid":false,"given":"Bing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2143-5666","authenticated-orcid":false,"given":"Jiale","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengcheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4753-8161","authenticated-orcid":false,"given":"Di","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9026-4613","authenticated-orcid":false,"given":"Shivakumara","family":"Palaiahnakote","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113693_b1","article-title":"GrabPhisher: Phishing scams detection in ethereum via temporally evolving GNNs","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Serv. Comput."},{"key":"10.1016\/j.patcog.2026.113693_b2","article-title":"Geometric and topological structure-induced large-scale graph learning for social and information networks","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113693_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111921","article-title":"Hypergraph-based semantic and topological self-supervised learning for brain disease diagnosis","volume":"169","author":"Han","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113693_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110940","article-title":"NLA-GNN: Non-local information aggregated graph neural network for heterogeneous graph embedding","volume":"158","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113693_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112055","article-title":"Multi-head graph contrastive learning with hop augmentation for node classification","volume":"170","author":"Zou","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113693_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111889","article-title":"Graph Perceiver IO: A general architecture for graph-structured data","volume":"169","author":"Bae","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113693_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110977","article-title":"Group link prediction in bipartite graphs with graph neural networks","volume":"158","author":"Luo","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113693_b8","series-title":"2023 International Joint Conference on Neural Networks","first-page":"1","article-title":"Rethinking the trigger-injecting position in graph backdoor attack","author":"Xu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113693_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110449","article-title":"Multi-target label backdoor attacks on graph neural networks","volume":"152","author":"Wang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113693_b10","unstructured":"Z. Xi, R. Pang, S. Ji, T. Wang, Graph backdoor, in: 30th USENIX Security Symposium, USENIX Security 21, 2021, pp. 1523\u20131540."},{"key":"10.1016\/j.patcog.2026.113693_b11","article-title":"TSBA: A two-stage poison-only backdoor attack on visual object tracking","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113693_b12","article-title":"FLPurifier: Backdoor defense in federated learning via decoupled contrastive training","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.patcog.2026.113693_b13","doi-asserted-by":"crossref","unstructured":"Z. Guan, M. Du, N. Liu, XGBD: Explanation-Guided Graph Backdoor Detection, in: European Conference on Artificial Intelligence, 2023.","DOI":"10.3233\/FAIA230363"},{"key":"10.1016\/j.patcog.2026.113693_b14","doi-asserted-by":"crossref","DOI":"10.1109\/TIFS.2025.3613061","article-title":"Identifying backdoored graphs in graph neural network training: An explanation-based approach with novel metrics","author":"Downer","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.patcog.2026.113693_b15","series-title":"International Conference on Algorithms and Architectures for Parallel Processing","first-page":"163","article-title":"Black-box graph backdoor defense","author":"Yang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113693_b16","series-title":"International Conference on Wireless Artificial Intelligent Computing Systems and Applications","first-page":"402","article-title":"E-SAGE: Explainability-based defense against backdoor attacks on graph neural networks","author":"Yuan","year":"2024"},{"key":"10.1016\/j.patcog.2026.113693_b17","doi-asserted-by":"crossref","unstructured":"H. Yu, C. Ma, X. Wan, J. Wang, T. Xiang, M. Shen, X. Liu, DShield: Defending against Backdoor Attacks on Graph Neural Networks via Discrepancy Learning, in: Network and Distributed System Security Symposium, NDSS, 2025.","DOI":"10.14722\/ndss.2025.240798"},{"key":"10.1016\/j.patcog.2026.113693_b18","unstructured":"Z. Zhang, M. Lin, J. Xu, Z. Wu, E. Dai, S. Wang, Robustness-inspired defense against backdoor attacks on graph neural networks, in: The Thirteenth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.patcog.2026.113693_b19","doi-asserted-by":"crossref","first-page":"47230","DOI":"10.1109\/ACCESS.2019.2909068","article-title":"Badnets: Evaluating backdooring attacks on deep neural networks","volume":"7","author":"Gu","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.patcog.2026.113693_b20","series-title":"2024 IEEE Symposium on Security and Privacy","first-page":"29","article-title":"Distribution preserving backdoor attack in self-supervised learning","author":"Tao","year":"2023"},{"key":"10.1016\/j.patcog.2026.113693_b21","series-title":"2024 IEEE Symposium on Security and Privacy","first-page":"2013","article-title":"BadVFL: Backdoor attacks in vertical federated learning","author":"Naseri","year":"2024"},{"key":"10.1016\/j.patcog.2026.113693_b22","unstructured":"K. Huang, Y. Li, B. Wu, Z. Qin, K. Ren, Backdoor Defense via Decoupling the Training Process, in: International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.patcog.2026.113693_b23","series-title":"2023 IEEE Symposium on Security and Privacy","first-page":"755","article-title":"Redeem myself: Purifying backdoors in deep learning models using self attention distillation","author":"Gong","year":"2023"},{"key":"10.1016\/j.patcog.2026.113693_b24","series-title":"2023 IEEE Symposium on Security and Privacy","first-page":"1311","article-title":"Rab: Provable robustness against backdoor attacks","author":"Weber","year":"2023"},{"key":"10.1016\/j.patcog.2026.113693_b25","series-title":"2023 IEEE Symposium on Security and Privacy","first-page":"737","article-title":"Baybfed: Bayesian backdoor defense for federated learning","author":"Kumari","year":"2023"},{"key":"10.1016\/j.patcog.2026.113693_b26","doi-asserted-by":"crossref","unstructured":"Z. Zhang, J. Jia, B. Wang, N.Z. Gong, Backdoor attacks to graph neural networks, in: Proceedings of the 26th ACM Symposium on Access Control Models and Technologies, 2021, pp. 15\u201326.","DOI":"10.1145\/3450569.3463560"},{"key":"10.1016\/j.patcog.2026.113693_b27","article-title":"Motif-backdoor: Rethinking the backdoor attack on graph neural networks via motifs","author":"Zheng","year":"2023","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.patcog.2026.113693_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106097","article-title":"Explanatory subgraph attacks against Graph Neural Networks","volume":"172","author":"Wang","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.patcog.2026.113693_b29","doi-asserted-by":"crossref","unstructured":"J. Xu, S. Picek, Poster: Clean-label backdoor attack on graph neural networks, in: Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, 2022, pp. 3491\u20133493.","DOI":"10.1145\/3548606.3563531"},{"key":"10.1016\/j.patcog.2026.113693_b30","doi-asserted-by":"crossref","unstructured":"J. Xu, M. Xue, S. Picek, Explainability-based backdoor attacks against graph neural networks, in: Proceedings of the 3rd ACM Workshop on Wireless Security and Machine Learning, 2021, pp. 31\u201336.","DOI":"10.1145\/3468218.3469046"},{"key":"10.1016\/j.patcog.2026.113693_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128133","article-title":"A semantic backdoor attack against graph convolutional networks","volume":"600","author":"Dai","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.113693_b32","series-title":"International Conference on Machine Learning","first-page":"40888","article-title":"Graph contrastive backdoor attacks","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113693_b33","doi-asserted-by":"crossref","unstructured":"E. Dai, M. Lin, X. Zhang, S. Wang, Unnoticeable backdoor attacks on graph neural networks, in: Proceedings of the ACM Web Conference 2023, 2023, pp. 2263\u20132273.","DOI":"10.1145\/3543507.3583392"},{"key":"10.1016\/j.patcog.2026.113693_b34","doi-asserted-by":"crossref","unstructured":"Z. Zhang, M. Lin, E. Dai, S. Wang, Rethinking graph backdoor attacks: A distribution-preserving perspective, in: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024, pp. 4386\u20134397.","DOI":"10.1145\/3637528.3671910"},{"key":"10.1016\/j.patcog.2026.113693_b35","article-title":"Gnnexplainer: Generating explanations for graph neural networks","volume":"32","author":"Ying","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113693_b36","article-title":"D4explainer: In-distribution explanations of graph neural network via discrete denoising diffusion","volume":"36","author":"Chen","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113693_b37","article-title":"Towards inductive and efficient explanations for graph neural networks","author":"Luo","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113693_b38","doi-asserted-by":"crossref","unstructured":"H. Yuan, J. Tang, X. Hu, S. Ji, Xgnn: Towards model-level explanations of graph neural networks, in: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, pp. 430\u2013438.","DOI":"10.1145\/3394486.3403085"},{"key":"10.1016\/j.patcog.2026.113693_b39","article-title":"Provably powerful graph networks","volume":"32","author":"Maron","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113693_b40","unstructured":"E. Jang, S. Gu, B. Poole, Categorical reparameterization with gumbel-softmax, in: The Fourth International Conference on Learning Representations, 2016."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006588?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006588?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:08:58Z","timestamp":1781298538000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006588"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":40,"alternative-id":["S0031320326006588"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113693","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Explanation-guided backdoor defense for ID and OOD attacks in graph neural networks","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113693","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113693"}}