Facebook is dealing with a major fake content problem — the company revealed last month that it removed 1.5 billion phony accounts between April and September this year alone. And while it’s encouraging that Facebook is detecting these fakes, there’s also a greater overall number of spam profiles hitting the platform, which means Facebook is struggling just to keep up. In fact, when it comes to rooting out spam, the company may be able to learn a thing or two from another social media app it owns: Instagram.

The popular photo-sharing platform recently announced sweeping changes to its security policies to comprehensively crack down on fake activity. The app will lean heavily on artificial intelligence to accomplish this.

“We will begin removing inauthentic likes, follows and comments from accounts that use third-party apps to boost their popularity,” Instagram announced in a blog post. “We’ve built machine learning tools to help identify accounts that use these services and remove the inauthentic activity.”

Of course, Instagram isn’t as large as Facebook, making it an easier platform to clean up. However, it’s encouraging how proactively the app is tackling the challenge of fake accounts. It’s a problem that Instagram’s massive parent company has, thus far, struggled to get its arms around.