Facebook Messenger uses Machine Learning to spot spammers, tightens the grip on security

Facebook Messenger is one of the company’s most successful standalone messaging apps ever after WhatsApp so it is natural for the firm to make it more secure. So, it is now using machine learning to make Messenger accounts more secure from unwanted contacts and scams.

Safety Notices is one of the features that is coming to Messenger. These pop up in a chat and provide tips to help users spot suspicious activity. Based on this they can block or ignore a user. Facebook’s Director of Product Management, Messenger Privacy and Safety, Jay Sullivan says that this has started rolling out for Android in March and will be coming to iOS users by next week.

However, Sullivan says that Facebook does not read your chats to determine suspicious activity, it instead uses machine learning. “We developed these safety tips with machine learning that looks at behavioral signals like an adult sending a large amount of friend or message requests to people under 18. This ensures that the new features will be available and effective when Messenger is end-to-end encrypted,” Sullivan added.

Also read: Facebook now lets you lock your profile so others can't download your full-size photos, get more information

While spotting a scammer or a fake account can be difficult for users at times, the safety notices in Messenger also educate users on ways to spot scams or imposters and help them take action.

In addition, Messenger has a new feature that educates minors (people under 18) to be cautious when interacting with an adult they may not know. It also helps them to take appropriate actions before responding to a message. “We are always consulting with experts on the best ways to keep minors safe and we’re encouraged when they express confidence in safety features like this,” says Sullivan.