{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:38:39Z","timestamp":1761176319047,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Annually, banks report billions in fraud on card networks, most of which can be attributed to breaches of card details, which are subsequently used to carry out fraudulent transactions. With the rise in digital payments, institutions consistently face the threat of data breaches, wherein various digital services are compromised to obtain sensitive details. Detecting such breaches and, subsequently, the cards they affect can help banks avoid future fraud. Recently, graph neural networks (GNNs) have gained significant influence in the domain of representation learning, and many works have extended the power of GNNs to solve the fraud detection problem in card payment networks. Despite these developments, incorporating information regarding events leading to fraud, such as breach location, testing of cards, or sale of cards on the dark web, has not been explored, thereby limiting the effectiveness of the fraud detection system. We propose a novel way of combining the information mentioned above in a bipartite graph. We further propose a customized training approach that leverages multiple losses to enhance model performance. To effectively handle the heterogeneity of nodes and their neighborhoods, we employ a tailored message-passing rule alongside an attention mechanism designed to extract semantic information from multiple layers. We show that the enriched graph, in addition to the proposed model, performs better than the baselines via experimentation on a real-world payment network.<\/jats:p>","DOI":"10.3233\/faia251476","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:03:43Z","timestamp":1761127423000},"source":"Crossref","is-referenced-by-count":0,"title":["BiGReachFRauD: Bipartite Graph Representation Learning Using Breached Sources for Financial Fraud Detection"],"prefix":"10.3233","author":[{"given":"Manasvi","family":"Aggarwal","sequence":"first","affiliation":[{"name":"MasterCard AI Garage, Gurgaon, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suhas","family":"Powar","sequence":"additional","affiliation":[{"name":"MasterCard AI Garage, Gurgaon, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepanshu","family":"Bagotia","sequence":"additional","affiliation":[{"name":"MasterCard AI Garage, Gurgaon, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hariom","family":"Chaudhary","sequence":"additional","affiliation":[{"name":"Google, Bangalore, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yatin","family":"Katyal","sequence":"additional","affiliation":[{"name":"MasterCard AI Garage, Gurgaon, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:03:43Z","timestamp":1761127423000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251476"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251476","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}