When it comes to the Messenger platform, Facebook must walk a fine line with its security policies. The company has to protect users while simultaneously not infringing on their private messages. That’s why Facebook announced a new set of security measures this week for detecting scammers that relies solely on metadata, not the content of user messages.

The new feature relies on machine learning to analyze communications across Facebook’s billions of users in order to identify trends and troubling behavior. For instance, if an adult user sent lots of friend requests to minors, the AI system could identify a potential abusive account. Then, it will alert you when you receive a message that appears to come from one of these cybercriminals.

“We’re introducing safety notices in Messenger that will pop up in a chat and provide tips to help people spot suspicious activity and take action to block or ignore someone when something doesn’t seem right,” said Jay Sullivan, Facebook’s director of product management for Messenger privacy and safety. “As we move to end-to-end encryption, we are investing in privacy-preserving tools like this to keep people safe without accessing message content.”

This seems like something Facebook should’ve already been doing, so it’s good that the company finally got around to it. And the fact that it can offer these protections without violating its own end-to-end encryption is an added bonus.

Recommended Resources

The Choice of Tech Experts Worldwide. Try 90 days free of Bitdefender and experience the highest level of digital safety.

Surf the web truly incognito. Try Bitdefender Premium VPN, the ultra-fast VPN that keeps your online identity and activities safe from hackers, ISPs and snoops.

System Mechanic 14 – Make your computer run like new. Winner of 200+ Editor’s Choice awards!