{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:15:22Z","timestamp":1758672922947,"version":"3.44.0"},"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>Defending against adversarial attacks on graphs has become increasingly important. Graph refinement to enhance the quality and robustness of representation learning is a critical area that requires thorough investigation. We observe that representations learned from attacked graphs are often ineffective for refinement due to perturbations that cause the endpoints of perturbed edges to become more similar, complicating the defender's ability to distinguish them. To address this challenge, we propose a robust unsupervised graph learning framework that utilizes cleaner graphs to learn effective representations. Specifically, we introduce an anomaly detection model based on contrastive learning to obtain a rough graph excluding a large number of perturbed structures. Subsequently, we then propose the Graph Pollution Degree (GPD), a mutual information-based measure that leverages the encoder's representation capability on the rough graph to assess the trustworthiness of the predicted graph and refine the learned representations. Extensive experiments on four benchmark datasets demonstrate that our method outperforms nine state-of-the-art defense models, effectively defending against adversarial attacks and enhancing node classification performance.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/311","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"2793-2801","source":"Crossref","is-referenced-by-count":0,"title":["Exploiting Self-Refining Normal Graph Structures for Robust Defense against Unsupervised Adversarial Attacks"],"prefix":"10.24963","author":[{"given":"Bingdao","family":"Feng","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Jin","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University"},{"name":"Key Laboratory of Artificial Intelligence Application Technology, Qinghai Minzu University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University"},{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongxiao","family":"He","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyi","family":"Cao","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cybersecurity, Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","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":"2025-09-23T11:33:40Z","timestamp":1758627220000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/311"}},"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\/311","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}