PayPal is launching a new AI-powered scam alert system globally, including on its Venmo platform, to protect users from increasingly sophisticated fraud, particularly for “Friends and Family” transactions.
According to Yigit Yildirim, SVP of global fraud prevention at PayPal, the company is combating AI used by bad actors with more intelligent AI used for good, stating, “We need to be smarter and faster than the scammers, and we’re combating AI used by bad actors with more intelligent AI used for good.” The new system provides dynamic warnings, with the level of action taken dependent on the risk assessment of the transaction. Higher-risk transactions will trigger more restrictive actions, potentially even blocking payments if there is a high confidence level that the transaction is a scam. In contrast, lower-risk alerts will prompt users to verify the safety of the transaction.
The AI models powering this system are continuously learning from billions of data points. This enables them to adapt to new types of scams, even those they have not been specifically trained on. By understanding the similarities between known scams and emerging ones, the system can identify novel fraud patterns. The new information gathered from these detections is stored for future use, enhancing the system’s ability to detect and prevent scams over time.
