An altered image of real news into fake news can be spotted by Facebook’s improved algorithm.

Facebook Tweaks AI Tools to Better Spot Bad Info, Hate Speech

According to a story on, Facebook CTO Mike Schroepfer said yesterday that the company has improved its AI detection of false COVID-19 posts, particularly in terms of analyzing images.

“What we want to be able to do is detect those things as being identical because they are, to a person, the same thing,” said Schroepfer. “Our previous systems were very accurate, but they were very fragile and brittle to even very small changes. If you change a small number of pixels, we were too nervous that it was different, and so we would mark it as different and not take it down. What we did here over the last two and a half years is build a neural net-based similarity detector that allowed us to better catch a wider variety of these variants again at very high accuracy.”

The Facebook AI discerned the original image and compared it to the altered one.

The neural net algorithm, called SimSearchNet, finds and analyzes similar images on Facebook and Instagram, numbering in the billions each day. The algorithm also tracks whether items that are not allowed on Facebook Marketplace, like an N95 face mask, are for sale, identifying photos that have been altered in an effort to fool the AI.

Another focus of the AI is hate speech, which can be devilishly difficult for AI to pick out of memes.

“The problem is that the meaning of these posts often results from an interplay between the image and the text. Words that would be perfectly appropriate or ambiguous on their own have their meaning clarified by the image on which they appear. Not only that, but there’s an endless number of variations in images or phrasings that can subtly change (or not change) the resulting meaning.”

To address the problem, Facebook is launching a “Hateful Memes Challenge” later this year to help train the machine learning AI. Since the company’s 15,000 moderation contractors are at home with paid leave, the company is leaning heavily on AI to moderate content, planning to continue its efforts more heavily in that area into the future.