{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:55:52Z","timestamp":1773802552411,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"18","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Multi-domain graph pre-training has emerged as a pivotal technique in developing graph foundation models. \nWhile it greatly improves the generalization of graph neural networks, its privacy risks under membership inference attacks (MIAs), which aim to identify whether a specific instance was used in training (member), remain largely unexplored.\nHowever, effectively conducting MIAs against multi-domain graph pre-trained models is a significant challenge due to:\n(i) Enhanced Generalization Capability: Multi-domain pre-training reduces the overfitting characteristics commonly exploited by MIAs.\n(ii) Unrepresentative Shadow Datasets: Diverse training graphs hinder the obtaining of reliable shadow graphs.\n(iii) Weakened Membership Signals: Embedding-based outputs offer less informative cues than logits for MIAs.\nTo tackle these challenges, we propose MGP-MIA, a novel framework for Membership Inference Attacks against Multi-domain Graph Pre-trained models.\nSpecifically, we first propose a membership signal amplification mechanism that amplifies the overfitting characteristics of target models via machine unlearning. \nWe then design an incremental shadow model construction mechanism that builds a reliable shadow model with limited shadow graphs via incremental learning.\nFinally, we introduce a similarity-based inference mechanism that identifies members based on their similarity to positive and negative samples.\nExtensive experiments demonstrate the effectiveness of our proposed MGP-MIA and reveal the privacy risks of multi-domain graph pre-training.<\/jats:p>","DOI":"10.1609\/aaai.v40i18.38576","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:38:09Z","timestamp":1773794289000},"page":"15483-15491","source":"Crossref","is-referenced-by-count":0,"title":["Privacy Auditing of Multi-Domain Graph Pre-Trained Model Under Membership Inference Attacks"],"prefix":"10.1609","volume":"40","author":[{"given":"Jiayi","family":"Luo","sequence":"first","affiliation":[]},{"given":"Qingyun","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Yuecen","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Haonan","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Xingcheng","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Jianxin","family":"Li","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38576\/42538","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38576\/42538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:38:09Z","timestamp":1773794289000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38576"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i18.38576","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}