Visa's neural network assesses more than 500 risk attributes in about a millisecond to predict every transaction's fraud probability.
Data released by AusPayNet suggests it is working, as overall card fraud only rose 0.6% in 2020, even though online retail spending grew 44%.
Enumeration attacks – an automated, brute force approach that guesses and tests payment credentials such as account numbers, CVV2, and/or expiry dates during online checkout – came to the fore locally and internationally during the past year.
Visa's AI-powered technology is able to spot patterns in data that would be undetectable by humans, and then alert affected merchants and financial institutions before fraudulent transactions begin.
"We have a global team of around 850 Visa employees dedicated to anticipating and countering new threats as fraudsters find new ways to attack," said Visa head of risk for Australia, New Zealand and South Pacific Carolina Gallegos.
"Trust underpins everything we do at Visa, including our approach to innovation. We are investing more heavily than ever in systems resilience, fraud management and cybersecurity, including tokenisation, AI and blockchain-based solutions to bring even more security to ecommerce and Australian businesses."
In related news, new Visa-commissioned independent research conducted in May by strategy consultancy Clear surveyed 2045 Australian debit cardholders, and found security benefits were considered important.
Almost three in four consumers (73%) considered fraudulent purchase protection a very important card benefit, with the confidentiality of personal data and receiving fraudulent purchase alerts were equal second at 70%.