Mastercard's real-time fraud detection technology will get a boost later this year when it introduces the generative AI fraud detection tool it has developed.
AI tool, called Decision Intelligence Pro (DI Pro) is powered by a recurrent neural network developed internally by Mastercard's cybersecurity and anti-fraud teams. The fraud detection algorithm is trained on the billions of transactions Mastercard processes every year.
The model learns from the cardholder's purchase history to understand the relationship between merchants and cardholders. When a cardholder initiates a transaction, DI Pro scans a trillion data points to predict whether the transaction will be fake or not. Determines the likelihood that the cardholder will execute a transaction with the company based on the trader's visit history.
In less than 50 milliseconds, DI Pro can predict whether a transaction is likely authentic or should be flagged as fraudulent. DI Pro is expected to be implemented later this year, but initial modelling shows it could increase fraud detection rates by an average of 20%, and in some cases up to 300%.
“With generative AI, we are transforming the speed and accuracy of our anti-fraud solutions, deterring criminals’ efforts and protecting banks and their clients. Recharging our algorithm further will improve our ability to predict the next potential fraudulent event, inspiring confidence in any interaction,” said Ajay Bhalla, President of Cyber and Intelligence at Mastercard.
In addition to protecting cardholders from fraud, Bhalla said that DI Pro would also “reduce the number of false positives by more than 85%’ Banks spend a significant part of their operating costs on fraud detection. Decrease in fraudulent transactions by 20% means reducing the human and financial resources needed to assess illegitimate transactions.
Cyber threats are becoming a growing problem in the business world. and companies are increasingly investing in Educating employees or the development and implementation of business protection solutions. The seriousness of these threats has become clear in the case of the Hong Kong company, which deep fake The scam lost $26 million.
Specifically, pThe fraud started with a misleading email, allegedly from a UK-based company's financial director, inviting an employee to a video call to discuss a confidential financial transaction. These scammers used deep fake generated by artificial intelligence in order to imitated the look and voice of older colleagues employees, including the Chief Financial Officer (CFO), during a videoconference call.
AI deep fakes have been used for a range of scams, including several targeted political and public figures such as Elon Musk and Mr. Beast and British Prime Minister Rishi Sunak. Studies show that people can no longer reliably distinguish facial rights from sophisticated counterfeits, and about 1/4 of people are deceived by the voices generated by artificial intelligence.
EDIH Adria can help you strengthen your company's resilience against cyber attacks. Contact us at info@edihadria.eu and find the best solution with our experts!
English 
Croatian 
Italian