AI-Driven Security: Mastercard's New Approach to Preventing Card Fraud

Mastercard is harnessing the power of artificial intelligence to enhance its fraud detection technology, enabling faster identification and replacement of compromised credit and debit cards before they can be exploited by criminals

by Sededin Dedovic
SHARE
AI-Driven Security: Mastercard's New Approach to Preventing Card Fraud
© SLN! Media Group / YOutube channel

Mastercard is implementing artificial intelligence in fraud prediction technology to detect compromised credit and debit cards faster, enabling banks to replace them before criminals can use them. On Wednesday, Mastercard announced that it expects to be able to detect when your credit or debit card number is compromised before it reaches cybercriminals.

In its latest software update to be rolled out this week, Mastercard is integrating artificial intelligence into its fraud prediction technology, which is expected to identify patterns of stolen cards more quickly and enable banks to replace them before they are used by criminals.

Johan Gerber, executive vice president for security and cyber innovation at Mastercard, said in an interview: "Generative AI will enable us to detect where you potentially compromised your data, to identify how it could have happened, and to resolve that situation very quickly not just for you, but for other customers who don’t know they’re compromised." Headquartered in Purchase, New York, Mastercard can now use other patterns or contextual information, such as geography, time, and addresses, and combine them with incomplete but compromised credit card numbers appearing in databases to more quickly reach cardholders and replace them before criminals can use them.

Patterns can also be used in reverse, potentially using batches of bad cards to identify compromised merchants or payment processors. Pattern recognition goes beyond what humans can do through database queries or other standard methods, Gerber said.

Billions of stolen credit and debit card numbers circulate on the dark web, available for purchase by any criminal. Most are stolen from merchants over the years in data breaches, but a significant number are stolen from less vigilant consumers who used their credit or debit cards at the wrong gas station, ATM, or online merchant.

A window sticker advertising Visa and MasterCard credit cards© Justin Sullivan / Getty Images

These compromised cards can remain undetected for weeks, months, or even years. It’s only when payment networks dive into the dark web to find stolen numbers, or when a merchant discovers a data leak, or when a card is used by a criminal, that payment networks and banks realize a batch of cards might be compromised.

"We can now proactively contact banks to ensure we provide service to that consumer and deliver them a new card as quickly as possible, so they can get on with their lives with minimal disruption," Gerber said. Payment networks generally try to move away from “static” credit or debit card numbers—that is, the card number and expiration date used universally with all merchants—and transition to unique numbers for specific transactions.

But it may take years for this transition to happen, especially in the U.S., where payment technology adoption typically lags. While over 90% of all live transactions globally now use chip cards, that figure in the U.S. is closer to 70%, according to EMVCo, the technology organization behind the chip in credit and debit cards.

Technological Advances and Challenges

Mastercard's update comes as its main competitor, Visa Inc., also seeks ways for consumers to move away from 16-digit credit and debit card numbers. Last week, Visa announced significant changes in how credit and debit cards will function in the U.S., meaning Americans will carry fewer physical cards in their wallets, and the 16-digit credit or debit card numbers printed on each card will become increasingly irrelevant.

Visa also announced it would rely more on tokenization, a technology that replaces sensitive card data with a unique identifier or token. Tokens can be used for specific transactions and are useless to anyone who intercepts them, further reducing the risk of fraud, reports Fortune.

These latest advancements in pattern recognition and fraud prediction technology are part of a broader trend in the financial services industry, increasingly relying on artificial intelligence. AI technology enables companies like Mastercard and Visa to identify and respond to potential threats much faster than was previously possible.

However, there are several challenges associated with this technology. First, there is a need for vast amounts of data for AI models to learn and recognize patterns. This means companies must invest in infrastructure to collect and store this data, as well as in technology for its analysis.

Second, as AI models become more complex, there is also a risk of errors or biases in their algorithms. This can lead to false positives or negatives, which can negatively impact users. Finally, there is the issue of privacy.

Collecting and analyzing large amounts of user data can raise concerns about privacy protection. Companies must ensure they comply with all relevant data protection laws and regulations and implement appropriate security measures to protect their users' data.

Despite these challenges, the future of AI in financial services looks bright. Technology like the one Mastercard is now introducing has the potential to drastically reduce the incidence of fraud and provide users with a higher level of security.

SHARE