Visa Inc (NYSE:V), a leader in digital payments, announced updates to its Visa Account Attack Intelligence (VAAI) offering with the addition of VAAI Score, a new tool that uses productive AI to detect and score enumeration attacks .
VAAI Score, which will be available first to US issuers, will help reduce fraud and operational losses by assigning each transaction a real-time risk score to detect and prevent card-not-present transaction enumeration attacks (CNP).
Visa’s VAAI score identifies the likelihood of sophisticated enumeration attacks in real-time to help reduce fraud without compromising the integrity of Visa’s performance and accuracy. The tool was able to reduce the false positive rate by 85% compared to other risk models, as the VAAI Score focuses on specific signals to enumerate allowing for a stronger performance.
VAAI Score can help publishers with:
- Reduced fraud and operational losses: Helps detect complex enumeration attacks in real-time, which can help reduce verified account fraud and operational losses due to enumeration, such as call center calls and card reissuance, and helps protect customers .
- Improved cardholder experience: Helps detect when legitimate cardholder transactions are not affected, while providing issuers with a tool to proactively decline transactions at risk of enumeration attacks.
- Real-time transaction scoring: Provides real-time risk scoring in 20 milliseconds4 that can help clients identify enumeration and use it in authorization decisions when used with a rules engine.
The VAAI Score model has been trained on more than 15 billion VisaNet transactions and has six times the number of features compared to previous VAAI models to help better evaluate suspicious enumeration transactions. Visa’s approach uses noisy data to train its highly accurate AI model in real time. By evaluating each CNP transaction against enumeration patterns, the new risk scoring model outputs a two-digit risk score that helps predict enumeration probability to better determine when the transaction will be approved and rejected.