Getty Images / SOPA Images / Contributor
Cybersecurity is a cat-and-mouse game, with new technologies providing more sophisticated protections — and threats. That has only accelerated with generative AI, which has led to even more advanced attacks, but PayPal is now leveraging it to stay ahead.
PayPal, which also owns the digital payment platform Venmo, has added a new, dynamic, AI-powered scam alert system to its fraud prevention initiative, which is meant to keep its worldwide ecosystem of users safer and combat scammers with quickly evolving tactics.
Also: I clicked on four sneaky online scams on purpose – to show you how they work
“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,” said Yigit Yildirim, SVP of global fraud prevention at PayPal.
AI-powered scam alerts
PayPal is rolling out AI-powered scam alerts for Friends and Family transactions on the PayPal platform globally and Venmo in the US. This alert system lets users know before they send money if something is a potential scam, as seen in the image below.
PayPal
Depending on the level of risk detected, the alert will show different warnings about the likelihood of each transaction being a scam, adding more friction as the risk increases.
For example, at the highest confidence of a scam, it will block the payment from moving forward. For potential risks in which fewer risky signals are detected, it will take less drastic action, such as sending alerts encouraging users to verify safety or recommending actions.
Also: Think your Venmo is private? You should double-check this setting
PayPal said the differentiating alerts were intentionally chosen to improve fraud prevention effectiveness. The company also said that if a customer receives the same static warning every day, users will be more inclined to ignore it.
“Consider this scenario we worked to avoid: If you send the same friend money for lunch every week but always receive the same generic warning to watch out for scams, it not only interferes with your payment experience, but it leads you to ignore the warnings altogether,” said Yildirim.
How does it work?
To power the alerts and detect risk signals, PayPal uses continually learning AI models that can adapt to the emergence of new types of scams, detecting scams they weren’t necessarily trained on by analyzing billions of data points and updating themselves when patterns change.
Also: How AI agents help hackers steal your confidential data – and what to do about it
“With continually learning models, our AI can understand similarities between a known and a new scam and help us detect the new one. Backed by our risk controls and research, the AI is leveraged to alert customers to a potential scam, even if we have not seen that exact same scam before,” said Yildirim.
Moreover, the model will then remember this new information for future scam detection efforts.
Get the morning’s top stories in your inbox each day with our Tech Today newsletter.
