{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:04:24Z","timestamp":1775815464153,"version":"3.50.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>Graph learning models have been empirically proven to be vulnerable to backdoor threats, wherein adversaries submit trigger-embedded inputs to manipulate the model predictions. \n\nCurrent graph backdoor defenses manifest several limitations: 1) dependence on model-related details, 2) necessitation of additional fine-tuning, and 3) reliance on extra explainability tools, all of which are infeasible under stringent privacy policies. \n\nTo address those limitations, we propose GraphProt, a certified black-box defense method to suppress backdoor attacks on GNN-based graph classifiers. Our GraphProt operates in a model-agnostic manner and solely leverages graph input.\n\nSpecifically, GraphProt first introduces designed topology-feature-filtration to mitigate graph anomalies. Subsequently, subgraphs are sampled via a formulated strategy integrating topology and features, followed by a robust model inference through a majority vote-based subgraph prediction ensemble.\n\nOur results across benchmark attacks and datasets show GraphProt effectively reduces attack success rates while preserving regular graph classification accuracy.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/70","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"619-627","source":"Crossref","is-referenced-by-count":3,"title":["GraphProt: Certified Black-Box Shielding Against Backdoored Graph Models"],"prefix":"10.24963","author":[{"given":"Xiao","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuni","family":"Lai","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaolei","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cornell University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","theme":"Artificial Intelligence","location":"Montreal, Canada","acronym":"IJCAI-2025","number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2025,8,16]]},"end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:32:49Z","timestamp":1758627169000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/70"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/70","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}