Fraud Detection
Fraudsters steal payment card numbers through spyware, malware, card skimming, and other clandestine methods, then post partial card numbers on illegal websites, making it difficult to identify compromised cards quickly enough to block fraud.
Reported impact
Mastercard says the generative AI enhancement lets it detect compromised cards faster and more accurately, helps identify at-risk merchants sooner, and enables banks to block and reissue cards more quickly to reduce fraud.
Mastercard implemented a generative AI-based predictive fraud detection capability within its card security operations to identify compromised payment cards and suspicious merchant exposure faster across its network. The system scans transaction data spanning billions of cards and millions of merchants to detect complex fraud patterns and predict the full details of cards that criminals partially expose on illegal websites. Mastercard says this enhancement strengthens its existing Cyber Secure security suite, which has been available since 2020 and maintains transparent cybersecurity information on bank and merchant online profiles, including suspected compromised cards. In practice, the AI-driven detection layer analyzes large-scale network activity, flags likely compromises, and feeds higher-speed, higher-accuracy alerts to banks so they can block and reissue cards and monitor attempted transactions to mitigate fraud.
Transaction data across billions of cards and millions of merchants is scanned to surface complex fraud patterns and predict full compromised card details from partial exposures; the resulting risk signals enhance Cyber Secure and trigger faster, more accurate alerts to banks, which can then block, reissue, and monitor affected cards.
"Cyber Secure, available since 2020, uses integrated technology to create a baseline of transparent cybersecurity information on bank and merchant online profiles in the payment ecosystem, including details of suspected compromised cards."
"Mastercard is using generative AI to double the speed at which it can detect potentially compromised cards"
"The new technology works by scanning transaction data across billions of cards and millions of merchants at faster rates than previously imaginable."
"Using generative AI-based predictive technology built by Mastercard it is able to protect future transactions against emerging threats"
"doubling the detection rate of compromised cards"
"increasing the speed of identifying merchants at-risk from - or compromised by - fraudsters by 300%."
"reducing false positives during the detection of fraudulent transactions against potentially compromised cards by up to 200%"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample Sep 24, 2026 Mastercard Fraudsters are using AI to find vulnerabilities, adapt tactics, and scale attacks across more payment channels, while traditional transaction-by-transaction controls struggle to catch coordinated fraud and authorized… Last year, scam losses globally were estimated at $442 billion In-house Sample Jan 21, 2026 Groupe BPCE Groupe BPCE wanted to transform banking operations and customer experience at scale, improving back-office productivity, frontline advisor support, mobile customer interactions, contact center automation, fraud… 1 million calls out of the 12 million received each year are handled from start to finish by an AI voice agent AI assistant · AI voice agent · Gen AI In-house Sample Sep 23, 2024 Zurich Insurance Group Zurich needed to review very large claims volumes more efficiently, reduce investigator drudgery and false positives, and detect fraudulent claims and emerging fraud patterns quickly enough to protect honest customers… a team of 50 specialists Allegro · Zurich’s internal AI chatbot · Zurich’s proprietary fraud scoring tool 