{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T04:42:05Z","timestamp":1772944925319,"version":"3.50.1"},"reference-count":67,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["62072109"],"award-info":[{"award-number":["62072109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Fujian Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2021J06013"],"award-info":[{"award-number":["2021J06013"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.inffus.2025.103536","type":"journal-article","created":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T17:45:03Z","timestamp":1753724703000},"page":"103536","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Dissecting vulnerability in information fusion process of Graph Convolutional Networks"],"prefix":"10.1016","volume":"126","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1106-1764","authenticated-orcid":false,"given":"Shuman","family":"Zhuang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5835-9903","authenticated-orcid":false,"given":"Zhihao","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Jicong","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Zhaoliang","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jiali","family":"Yin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9031-107X","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Ximeng","family":"Liu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2025.103536_b1","article-title":"Node-personalized multi-graph convolutional networks for recommendation","author":"Zhou","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.inffus.2025.103536_b2","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.neunet.2022.10.001","article-title":"Multi-aspect enhanced graph neural networks for recommendation","volume":"157","author":"Zhang","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.inffus.2025.103536_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106356","article-title":"G2ViT: Graph neural network-guided vision transformer enhanced network for retinal vessel and coronary angiograph segmentation","author":"Xu","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.inffus.2025.103536_b4","first-page":"1","article-title":"Graph representation learning in biomedicine and healthcare","author":"Li","year":"2022","journal-title":"Nat. Biomed. Eng."},{"key":"10.1016\/j.inffus.2025.103536_b5","series-title":"AAAI","first-page":"4115","article-title":"Knowledge-aware coupled graph neural network for social recommendation","author":"Huang","year":"2021"},{"key":"10.1016\/j.inffus.2025.103536_b6","series-title":"SIGKDD","first-page":"1007","article-title":"Learning dynamic context graphs for predicting social events","author":"Deng","year":"2019"},{"key":"10.1016\/j.inffus.2025.103536_b7","series-title":"ICLR","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.inffus.2025.103536_b8","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.neunet.2023.10.019","article-title":"Beyond the individual: An improved telecom fraud detection approach based on latent synergy graph learning","volume":"169","author":"Wu","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.inffus.2025.103536_b9","series-title":"AAAI","first-page":"4537","article-title":"Towards consumer loan fraud detection: Graph neural networks with role-constrained conditional random field","author":"Xu","year":"2021"},{"issue":"6","key":"10.1016\/j.inffus.2025.103536_b10","doi-asserted-by":"crossref","first-page":"6623","DOI":"10.1109\/TNSE.2024.3462462","article-title":"Graph anomaly detection via multi-view discriminative awareness learning","volume":"11","author":"Lian","year":"2024","journal-title":"IEEE Transactions on Network Science and Engineering"},{"key":"10.1016\/j.inffus.2025.103536_b11","series-title":"ICCV","first-page":"1","article-title":"GLA-GCN: Global-local adaptive graph convolutional network for 3D human pose estimation from monocular video","author":"Yu","year":"2023"},{"key":"10.1016\/j.inffus.2025.103536_b12","series-title":"CVPR","first-page":"5291","article-title":"Sigma: Semantic-complete graph matching for domain adaptive object detection","author":"Li","year":"2022"},{"key":"10.1016\/j.inffus.2025.103536_b13","article-title":"Attributed multi-order graph convolutional network for heterogeneous graphs","author":"Chen","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.inffus.2025.103536_b14","series-title":"IJCAI 2024","first-page":"2505","article-title":"Kernel readout for graph neural networks","author":"Yu","year":"2024"},{"key":"10.1016\/j.inffus.2025.103536_b15","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.neunet.2023.09.006","article-title":"Joint learning of feature and topology for multi-view graph convolutional network","volume":"168","author":"Chen","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.inffus.2025.103536_b16","series-title":"ICDE","first-page":"14","article-title":"Binarizedattack: Structural poisoning attacks to graph-based anomaly detection","author":"Zhu","year":"2022"},{"key":"10.1016\/j.inffus.2025.103536_b17","series-title":"SIGKDD","first-page":"2847","article-title":"Adversarial attacks on neural networks for graph data","author":"Z\u00fcgner","year":"2018"},{"key":"10.1016\/j.inffus.2025.103536_b18","series-title":"IJCAI","article-title":"Adversarial examples on graph data: Deep insights into attack and defense","author":"Wu","year":"2019"},{"key":"10.1016\/j.inffus.2025.103536_b19","series-title":"SIGKDD","first-page":"925","article-title":"Reliable representations make a stronger defender: Unsupervised structure refinement for robust gnn","author":"Li","year":"2022"},{"key":"10.1016\/j.inffus.2025.103536_b20","series-title":"AAAI","first-page":"9368","article-title":"Relation-aware graph attention model with adaptive self-adversarial training","author":"Qin","year":"2021"},{"key":"10.1016\/j.inffus.2025.103536_b21","article-title":"Spectral adversarial training for robust graph neural network","author":"Li","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.inffus.2025.103536_b22","series-title":"WSDM","first-page":"169","article-title":"All you need is low (rank) defending against adversarial attacks on graphs","author":"Entezari","year":"2020"},{"key":"10.1016\/j.inffus.2025.103536_b23","article-title":"FocusedCleaner: Sanitizing poisoned graphs for robust GNN-based node classification","author":"Zhu","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.inffus.2025.103536_b24","series-title":"SIGKDD","first-page":"1399","article-title":"Robust graph convolutional networks against adversarial attacks","author":"Zhu","year":"2019"},{"key":"10.1016\/j.inffus.2025.103536_b25","series-title":"NeurIPS","first-page":"9263","article-title":"Gnnguard: Defending graph neural networks against adversarial attacks","author":"Zhang","year":"2020"},{"key":"10.1016\/j.inffus.2025.103536_b26","series-title":"WWW","first-page":"328","article-title":"Robust mid-pass filtering graph convolutional networks","author":"Huang","year":"2023"},{"key":"10.1016\/j.inffus.2025.103536_b27","series-title":"ICLR","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"10.1016\/j.inffus.2025.103536_b28","series-title":"NeurIPS","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017"},{"key":"10.1016\/j.inffus.2025.103536_b29","series-title":"ICML","first-page":"21","article-title":"Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","author":"Abu-El-Haija","year":"2019"},{"key":"10.1016\/j.inffus.2025.103536_b30","series-title":"ICML","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","author":"Xu","year":"2018"},{"key":"10.1016\/j.inffus.2025.103536_b31","series-title":"SIGKDD","first-page":"2377","article-title":"Multiplex heterogeneous graph convolutional network","author":"Yu","year":"2022"},{"key":"10.1016\/j.inffus.2025.103536_b32","series-title":"ACM MM","first-page":"186","article-title":"Towards multi-view consistent graph diffusion","author":"Lu","year":"2024"},{"key":"10.1016\/j.inffus.2025.103536_b33","series-title":"ACM MM","first-page":"10065","article-title":"Enhancing multi-view graph neural network with cross-view confluent message passing","author":"Zhuang","year":"2024"},{"key":"10.1016\/j.inffus.2025.103536_b34","series-title":"AAAI","article-title":"Beyond graph convolutional network: An interpretable regularizer-centered optimization framework","author":"Wang","year":"2023"},{"key":"10.1016\/j.inffus.2025.103536_b35","series-title":"WWW","first-page":"1215","article-title":"Interpreting and unifying graph neural networks with an optimization framework","author":"Zhu","year":"2021"},{"key":"10.1016\/j.inffus.2025.103536_b36","doi-asserted-by":"crossref","first-page":"110364","DOI":"10.1016\/j.patcog.2024.110364","article-title":"Graph convolutional network with elastic topology","volume":"151","author":"Wu","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.inffus.2025.103536_b37","doi-asserted-by":"crossref","first-page":"8593","DOI":"10.1109\/TMM.2023.3260649","article-title":"Interpretable graph convolutional network for multi-view semi-supervised learning","volume":"25","author":"Wu","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.inffus.2025.103536_b38","series-title":"NeurIPS","first-page":"9720","article-title":"Graph neural networks with adaptive residual","author":"Liu","year":"2021"},{"key":"10.1016\/j.inffus.2025.103536_b39","series-title":"ICLR","article-title":"Adversarial attacks on graph neural networks via meta learning","author":"Zugner","year":"2019"},{"issue":"2","key":"10.1016\/j.inffus.2025.103536_b40","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1038\/s41562-017-0290-3","article-title":"Hiding individuals and communities in a social network","volume":"2","author":"Waniek","year":"2018","journal-title":"Nat. Hum. Behav."},{"key":"10.1016\/j.inffus.2025.103536_b41","series-title":"IJCAI","article-title":"Topology attack and defense for graph neural networks: An optimization perspective","author":"Xu","year":"2019"},{"key":"10.1016\/j.inffus.2025.103536_b42","first-page":"73079","article-title":"Towards stable representations for protein interface prediction","volume":"37","author":"Gao","year":"2024","journal-title":"NeurIPS"},{"key":"10.1016\/j.inffus.2025.103536_b43","article-title":"ERMAV: Efficient and robust graph contrastive learning via multiadversarial views training","author":"Li","year":"2025","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.inffus.2025.103536_b44","series-title":"WWW","article-title":"Robust graph learning against adversarial evasion attacks via prior-free diffusion-based structure purification","author":"Luo","year":"2025"},{"key":"10.1016\/j.inffus.2025.103536_b45","series-title":"AAAI","first-page":"4210","article-title":"Powerful graph convolutional networks with adaptive propagation mechanism for homophily and heterophily","author":"Wang","year":"2022"},{"key":"10.1016\/j.inffus.2025.103536_b46","series-title":"SIGKDD","first-page":"66","article-title":"Graph structure learning for robust graph neural networks","author":"Jin","year":"2020"},{"key":"10.1016\/j.inffus.2025.103536_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102296","article-title":"A graph transformer defence against graph perturbation by a flexible-pass filter","volume":"107","author":"Zhu","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2025.103536_b48","series-title":"AAAI","first-page":"13473","article-title":"Refine then classify: robust graph neural networks with reliable neighborhood contrastive refinement","author":"Zhuang","year":"2025"},{"key":"10.1016\/j.inffus.2025.103536_b49","series-title":"ACM MM","first-page":"10065","article-title":"Enhancing multi-view graph neural network with cross-view confluent message passing","author":"Zhuang","year":"2024"},{"key":"10.1016\/j.inffus.2025.103536_b50","series-title":"ICLR","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","author":"Gasteiger","year":"2018"},{"key":"10.1016\/j.inffus.2025.103536_b51","series-title":"ICML","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"10.1016\/j.inffus.2025.103536_b52","series-title":"ICML","first-page":"399","article-title":"Learning fast approximations of sparse coding","author":"Gregor","year":"2010"},{"issue":"4","key":"10.1016\/j.inffus.2025.103536_b53","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.1137\/080738970","article-title":"A singular value thresholding algorithm for matrix completion","volume":"20","author":"Cai","year":"2010","journal-title":"SIAM J. Optim."},{"key":"10.1016\/j.inffus.2025.103536_b54","series-title":"ICLR","article-title":"Deep layers as stochastic solvers","author":"Bibi","year":"2018"},{"key":"10.1016\/j.inffus.2025.103536_b55","series-title":"Deeprobust: A pytorch library for adversarial attacks and defenses","author":"Li","year":"2020"},{"key":"10.1016\/j.inffus.2025.103536_b56","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"vol. 33","author":"Hu","year":"2020"},{"key":"10.1016\/j.inffus.2025.103536_b57","first-page":"14498","article-title":"Scattering gcn: Overcoming oversmoothness in graph convolutional networks","volume":"vol. 33","author":"Min","year":"2020"},{"key":"10.1016\/j.inffus.2025.103536_b58","series-title":"ICLR","article-title":"Adagcn: Adaboosting graph convolutional networks into deep models","author":"Sun","year":"2019"},{"key":"10.1016\/j.inffus.2025.103536_b59","series-title":"SIGKDD","first-page":"1243","article-title":"Am-gcn: Adaptive multi-channel graph convolutional networks","author":"Wang","year":"2020"},{"key":"10.1016\/j.inffus.2025.103536_b60","series-title":"ICLR","article-title":"Simple spectral graph convolution","author":"Zhu","year":"2021"},{"key":"10.1016\/j.inffus.2025.103536_b61","series-title":"AAAI","first-page":"7949","article-title":"Deformable graph convolutional networks","author":"Park","year":"2022"},{"key":"10.1016\/j.inffus.2025.103536_b62","article-title":"Graph convolutional kernel machine versus graph convolutional networks","volume":"vol. 36","author":"Wu","year":"2024"},{"key":"10.1016\/j.inffus.2025.103536_b63","series-title":"WSDM","first-page":"148","article-title":"Node similarity preserving graph convolutional networks","author":"Jin","year":"2021"},{"key":"10.1016\/j.inffus.2025.103536_b64","series-title":"ICML","first-page":"6837","article-title":"Elastic graph neural networks","author":"Liu","year":"2021"},{"key":"10.1016\/j.inffus.2025.103536_b65","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2024.3403925","article-title":"Graph structure reshaping against adversarial attacks on graph neural networks","author":"Wang","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"11","key":"10.1016\/j.inffus.2025.103536_b66","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.inffus.2025.103536_b67","series-title":"ICML","first-page":"6878","article-title":"p-Laplacian based graph neural networks","author":"Fu","year":"2022"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253525006086?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253525006086?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T13:48:13Z","timestamp":1772891293000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253525006086"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":67,"alternative-id":["S1566253525006086"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2025.103536","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dissecting vulnerability in information fusion process of Graph Convolutional Networks","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2025.103536","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103536"}}