{"id":18415,"date":"2025-09-15T20:04:10","date_gmt":"2025-09-15T20:04:10","guid":{"rendered":"https:\/\/www.newsbeep.com\/il\/18415\/"},"modified":"2025-09-15T20:04:10","modified_gmt":"2025-09-15T20:04:10","slug":"swift-tests-use-of-ai-to-fight-cross-border-payment-fraud","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/il\/18415\/","title":{"rendered":"Swift Tests Use of AI to Fight Cross-Border Payment Fraud"},"content":{"rendered":"<p><a class=\"editor-rtfLink\" href=\"https:\/\/www.swift.com\/homepage\" target=\"_blank\" rel=\"noopener nofollow\">Swift<\/a> conducted tests to demonstrate the potential impact of artificial intelligence in preventing cross-border payments fraud.<\/p>\n<p>The global messaging system collaborated with 13 banks on experiments using privacy-enhancing technologies (PETs) to let institutions securely share fraud insights across borders, according to a Monday (Sept. 15) <a class=\"editor-rtfLink\" href=\"https:\/\/www.businesswire.com\/news\/home\/20250915499316\/en\/Swift-AI-Innovation-Creates-Blueprint-for-Banks-to-Stop-Fraud-Faster-Through-Cross-Border-Collaboration\" target=\"_blank\" rel=\"noopener nofollow\">press release<\/a>.<\/p>\n<p>In one instance, the PETs allowed participants to verify intelligence on suspicious accounts in real time, \u201ca development which could speed up the time taken to identify complex international financial crime networks and avoid fraudulent transactions being executed,\u201d the release said.<\/p>\n<p>In another case, participants employed a combination of PETs and federated learning, or an AI model that \u201cvisits\u201d institutions to train on their data locally and lets them work together without sharing customer information, to spot <a class=\"editor-rtfLink\" href=\"https:\/\/www.pymnts.com\/news\/artificial-intelligence\/2024\/swift-uses-ai-battle-cross-border-payment-fraud\/\" target=\"_blank\" rel=\"noopener nofollow\">anomalous transactions<\/a>, per the release.<\/p>\n<p>Trained using synthetic data from 10 million artificial transactions, the model was twice as effective in identifying fraud than a model trained using a single institution\u2019s dataset, the release said.<\/p>\n<p>\u201cThese experiments demonstrate the convening power of Swift as a trusted cooperative at the heart of global finance,\u201d <a class=\"editor-rtfLink\" href=\"https:\/\/www.linkedin.com\/in\/rachel-levi-ba7a9b128\" target=\"_blank\" rel=\"noopener nofollow\">Rachel Levi<\/a>, head of AI for Swift, said in the release. \u201cA united, industry-wide fraud defense will always be stronger than one put up by a single institution acting alone. The industry loses billions [of dollars] to fraud each year, but by enabling the secure sharing of intelligence across borders, we\u2019re paving the way for this figure to be significantly reduced and allowing fraud to be stopped in a matter of minutes, not hours or days.\u201d<\/p>\n<p>In the wake of these experiments, Swift plans to widen participation before beginning a second round of tests, which will use real transaction data in hopes of demonstrating the technologies\u2019 effect on real-world fraud, the release said.<\/p>\n<p>When it comes to preserving trust in financial transactions, <a class=\"editor-rtfLink\" href=\"https:\/\/www.pymnts.com\/data\/2025\/fraudsters-share-playbooks-so-why-wont-banks-share-data\/\" target=\"_blank\" rel=\"noopener nofollow\">sharing data<\/a> is important.<\/p>\n<p>\u201cIt\u2019s a team sport,\u201d <a class=\"editor-rtfLink\" href=\"https:\/\/www.entersekt.com\/\" target=\"_blank\" rel=\"noopener nofollow\">Entersekt<\/a> Chief Product Officer <a class=\"editor-rtfLink\" href=\"https:\/\/www.linkedin.com\/in\/pradheep\/\" target=\"_blank\" rel=\"noopener nofollow\">Pradheep Sampath<\/a> told PYMNTS in August. \u201cAnd the thread that binds us all together is data that\u2019s actionable, shared in good faith, and governed responsibly.\u201d<\/p>\n<p>For all PYMNTS AI coverage, subscribe to the daily <a href=\"https:\/\/pymnts.com\/subscribe\/\" target=\"_blank\" rel=\"noopener nofollow\">AI Newsletter<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"Swift conducted tests to demonstrate the potential impact of artificial intelligence in preventing cross-border payments fraud. The global&hellip;\n","protected":false},"author":2,"featured_media":0,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[],"class_list":["post-18415","post","type-post","status-publish","format-standard","category-artificial-intelligence"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/18415","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/comments?post=18415"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/18415\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media?parent=18415"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/categories?post=18415"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/tags?post=18415"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}