Researchers use machine learning to quickly detect video face swaps

This algorithm outperforms all other techniques that are currently available.

We all know that AI can be used to swap faces in photos and videos. People have, of course, taken advantage of this tool for some disturbing uses, including face-swapping people into pornographic videos -- the ultimate revenge porn. But if AI can be used to face swap, can't it also be used to detect when such a practice occurs? According to a new paper on, a new algorithm promises to do just that, identifying forged videos as soon as they are posted online.

The team, led by Andreas Rossler at the Technical University of Munich, developed machine learning that is able to automatically detect when videos are face swapped. They trained the algorithm using a large set of face swaps that they made themselves, creating the largest database of these kind of images available. They then trained the algorithm, called XceptionNet, to detect the face swaps.

XceptionNet clearly outperforms its rival techniques in detecting this kind of fake video, but it also actually improves the quality of the forgeries. Rossler's team can use the biggest hallmarks of a face swap to make the manipulation more seamless. It doesn't fool XceptionNet, but in the long run, it could make it harder for other methods to detect faked videos.