{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T01:04:37Z","timestamp":1789607077666,"version":"build-2803163510"},"reference-count":43,"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134594","type":"journal-article","created":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T17:27:15Z","timestamp":1785086835000},"page":"134594","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Certifying sparse node-feature robustness of graph neural networks via double-sampling randomized smoothing"],"prefix":"10.1016","volume":"701","author":[{"given":"Aimin","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4104-365X","authenticated-orcid":false,"given":"Xuyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuebo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbing","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.neucom.2026.134594_bib1","first-page":"1935","article-title":"Frontier progress of adversarial attacks and robustness evaluation of graph neural networks (in Chinese)","volume":"18","author":"Wu","year":"2024","journal-title":"J. Comput. Sci. Explor."},{"key":"10.1016\/j.neucom.2026.134594_bib2","unstructured":"M. Zhang, \"Research on adversarial robustness of graph neural networks\" (in Chinese), M.S. thesis, Beijing Univ. Posts Telecommun., Beijing, China, 2023."},{"key":"10.1016\/j.neucom.2026.134594_bib3","doi-asserted-by":"crossref","first-page":"2847","DOI":"10.1145\/3219819.3220078","article-title":"Adversarial attacks on neural networks for graph data","author":"Z\u00fcgner","year":"2018","journal-title":"Proc. 24th ACM SIGKDD Int. Conf. Knowl. Discov. Data Min."},{"key":"10.1016\/j.neucom.2026.134594_bib4","first-page":"1115","article-title":"Adversarial attack on graph structured data","author":"Dai","year":"2018","journal-title":"Proc. Int. Conf. Mach. Learn. (ICML)"},{"key":"10.1016\/j.neucom.2026.134594_bib5","doi-asserted-by":"crossref","first-page":"8954","DOI":"10.52202\/068431-0651","article-title":"Are defenses for graph neural networks robust?","volume":"35","author":"Mujkanovic","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.134594_bib6","first-page":"274","article-title":"Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples","author":"Athalye","year":"2018","journal-title":"Proc. Int. Conf. Mach. Learn. (ICML)"},{"key":"10.1016\/j.neucom.2026.134594_bib7","unstructured":"A. Madry, A. Makelov, L. Schmidt, et al., \"Towards deep learning models resistant to adversarial attacks,\" arXiv preprint arXiv:1706.06083, 2017."},{"issue":"1","key":"10.1016\/j.neucom.2026.134594_bib8","first-page":"190","article-title":"Survey on robustness of deep learning models (in Chinese)","volume":"45","author":"Ji","year":"2022","journal-title":"Chin. J. Comput."},{"key":"10.1016\/j.neucom.2026.134594_bib9","unstructured":"K. Xu, H. Zhang, S. Wang, et al., \"Fast and complete: Enabling complete neural network verification with rapid and massively parallel incomplete verifiers,\" arXiv preprint arXiv:2011.13824, 2020."},{"key":"10.1016\/j.neucom.2026.134594_bib10","first-page":"1310","article-title":"Certified adversarial robustness via randomized smoothing","author":"Cohen","year":"2019","journal-title":"Proc. Int. Conf. Mach. Learn. (ICML)"},{"key":"10.1016\/j.neucom.2026.134594_bib11","first-page":"656","article-title":"Certified robustness to adversarial examples with differential privacy","author":"Lecuyer","year":"2019","journal-title":"Proc. IEEE Symp. Secur. Priv. (SP)"},{"key":"10.1016\/j.neucom.2026.134594_bib12","article-title":"Certified adversarial robustness with additive noise","volume":"32","author":"Li","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.134594_bib13","unstructured":"L. Li, J. Zhang, T. Xie, et al., \"Double sampling randomized smoothing,\" arXiv preprint arXiv:2206.07912, 2022."},{"key":"10.1016\/j.neucom.2026.134594_bib14","first-page":"10693","article-title":"Randomized smoothing of all shapes and sizes","author":"Yang","year":"2020","journal-title":"Proc. Int. Conf. Mach. Learn. (ICML)"},{"key":"10.1016\/j.neucom.2026.134594_bib15","first-page":"2316","article-title":"Black-box certification with randomized smoothing: a functional optimization based framework","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.134594_bib16","first-page":"5286","article-title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","author":"Wong","year":"2018","journal-title":"Proc. Int. Conf. Mach. Learn. (ICML)"},{"key":"10.1016\/j.neucom.2026.134594_bib17","first-page":"246","article-title":"Certifiable robustness and robust training for graph convolutional networks","author":"Z\u00fcgner","year":"2019","journal-title":"Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discov. Data Min."},{"key":"10.1016\/j.neucom.2026.134594_bib18","series-title":"Proc. 26th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining","first-page":"1656","article-title":"Certifiable robustness of graph convolutional networks under structure perturbations","author":"Z\u00fcgner","year":"2020"},{"key":"10.1016\/j.neucom.2026.134594_bib19","first-page":"2718","article-title":"Certified robustness of community detection against adversarial structural perturbation via randomized smoothing","volume":"2020","author":"Jia","year":"2020","journal-title":"Proc. Web Conf."},{"key":"10.1016\/j.neucom.2026.134594_bib20","article-title":"Certifiable robustness to graph perturbations","volume":"32","author":"Bojchevski","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.134594_bib21","first-page":"1003","article-title":"Efficient robustness certificates for discrete data: sparsity-aware randomized smoothing for graphs, images and more","author":"Bojchevski","year":"2020","journal-title":"Proc. Int. Conf. Mach. Learn. (ICML)"},{"key":"10.1016\/j.neucom.2026.134594_bib22","unstructured":"J. Schuchardt, T. Wollschl\u00e4ger, A. Bojchevski, et al., \"Localized randomized smoothing for collective robustness certification,\" arXiv preprint arXiv:2210.16140, 2022."},{"key":"10.1016\/j.neucom.2026.134594_bib23","unstructured":"J. Schuchardt, A. Bojchevski, J. Gasteiger, et al., \"Collective robustness certificates: Exploiting interdependence in graph neural networks,\" arXiv preprint arXiv:2302.02829, 2023."},{"key":"10.1016\/j.neucom.2026.134594_bib24","first-page":"8463","article-title":"Certified robustness of graph convolution networks for graph classification under topological attacks","volume":"33","author":"Jin","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.134594_bib25","doi-asserted-by":"crossref","first-page":"1645","DOI":"10.1145\/3447548.3467295","article-title":"Certified robustness of graph neural networks against adversarial structural perturbation","author":"Wang","year":"2021","journal-title":"Proc. 27th ACM SIGKDD Conf. Knowl. Discov. Data Min."},{"key":"10.1016\/j.neucom.2026.134594_bib26","first-page":"16394","article-title":"Turning strengths into weaknesses: a certified robustness inspired attack framework against graph neural networks","author":"Wang","year":"2023","journal-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)"},{"key":"10.1016\/j.neucom.2026.134594_bib27","doi-asserted-by":"crossref","first-page":"33146","DOI":"10.52202\/068431-2402","article-title":"Randomized message-interception smoothing: gray-box certificates for graph neural networks","volume":"35","author":"Scholten","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.134594_bib28","first-page":"1596","article-title":"Structure-aware robustness certificates for graph classification","author":"Osselin","year":"2023","journal-title":"Proc. Uncertain. Artif. Intell. (UAI)"},{"issue":"15","key":"10.1016\/j.neucom.2026.134594_bib29","doi-asserted-by":"crossref","first-page":"13920","DOI":"10.1109\/JIOT.2023.3263384","article-title":"Toward certified robustness of graph neural networks in adversarial AIoT environments","volume":"10","author":"Lai","year":"2023","journal-title":"IEEE Internet Things J."},{"issue":"4","key":"10.1016\/j.neucom.2026.134594_bib30","doi-asserted-by":"crossref","first-page":"1597","DOI":"10.1109\/TKDE.2023.3311105","article-title":"Graph adversarial immunization for certifiable robustness","volume":"36","author":"Tao","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.neucom.2026.134594_bib31","doi-asserted-by":"crossref","unstructured":"Y. Lai, Y. Zhu, Y. Sun, et al., \"AuditVotes: A framework towards more deployable certified robustness for graph neural networks,\" arXiv preprint arXiv:2503.22998, 2025.","DOI":"10.1145\/3658644.3691376"},{"key":"10.1016\/j.neucom.2026.134594_bib32","unstructured":"T.N. Kipf, \"Semi-supervised classification with graph convolutional networks,\" arXiv preprint arXiv:1609.02907, 2016."},{"key":"10.1016\/j.neucom.2026.134594_bib33","article-title":"Provably robust deep learning via adversarially trained smoothed classifiers","volume":"32","author":"Salman","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.134594_bib34","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","author":"Yang","year":"2016","journal-title":"Proc. Int. Conf. Mach. Learn. (ICML)"},{"key":"10.1016\/j.neucom.2026.134594_bib35","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018","journal-title":"Proc. Int. Conf. Learn. Represent. (ICLR)"},{"key":"10.1016\/j.neucom.2026.134594_bib36","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.134594_bib37","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","first-page":"24574","article-title":"1-Lipschitz layers compared: Memory speed and certifiable robustness","author":"Prach","year":"2024"},{"key":"10.1016\/j.neucom.2026.134594_bib38","first-page":"25987","article-title":"Learn beneficial noise as graph augmentation","author":"Huang","year":"2025","journal-title":"Proc. 42nd Int. Conf. Mach. Learn. (ICML)"},{"issue":"11","key":"10.1016\/j.neucom.2026.134594_bib39","doi-asserted-by":"crossref","first-page":"7451","DOI":"10.1109\/TPAMI.2024.3392782","article-title":"Decouple graph neural networks: train multiple simple GNNs simultaneously instead of one","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134594_bib40","first-page":"05868","article-title":"Pitfalls of graph neural network evaluation","volume":"1811","author":"Shchur","year":"2018","journal-title":"arXiv Prepr. arXiv"},{"key":"10.1016\/j.neucom.2026.134594_bib41","first-page":"22118","article-title":"Open graph benchmark: datasets for machine learning on graphs","volume":"33","author":"Hu","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.neucom.2026.134594_bib42","article-title":"SEESAW: do graph neural networks improve node representation learning for all?","author":"Dong","year":"2025","journal-title":"J. Data-Centr Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.134594_bib43","first-page":"1539","article-title":"Article classification with graph neural networks and multigraphs","author":"Ly","year":"2024","journal-title":"Proc. LREC-COLING"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226019922?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226019922?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:27:55Z","timestamp":1789604875000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226019922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":43,"alternative-id":["S0925231226019922"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134594","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Certifying sparse node-feature robustness of graph neural networks via double-sampling randomized smoothing","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134594","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 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":"134594"}}