Some of the latest deepfakes are hard to distinguish from reality, but Facebook, in partnership with Michigan State University (MSU), have developed a method of detecting and attributing deepfakes that relies on reverse engineering from a single AI-generated image to the generative model used to produce it. That’s right, AI can now facilitate deepfake detection and tracing in real-world settings.
Current ways of determining deepfakes focus on telling whether an image is real, a deepfake (detection), or identifying whether an image was generated by a model seen during training. Reverse engineering relies on uncovering the unique patterns behind the AI model used to generate a single deepfake image. They start with image attribution and then work on discovering properties of the model that was used to generate the image.
- Transform your reality and do everything you love in totally new ways. Welcome to Meta Quest 3S. Now you can get the Batman: Arkham Shadow* and a...
- Explore thousands of unreal experiences with mixed reality, where you can blend digital objects into the room around you or dial up the immersion in...
- Have more fun with friends in Quest. Whether you’re stepping into an immersive game with people from around the world, watching a live concert...
Through this groundbreaking model parsing technique, researchers will now be able to obtain more information about the model used to produce particular deepfakes. Our method will be especially useful in real-world settings where the only information deepfake detectors have at their disposal is often the deepfake itself. In some cases, researchers may even be able to use it to tell whether certain deepfakes originate from the same model, regardless of differences in their outward appearance or where they show up online,” said Xi Yin, Research Scientist and Tal Hassner, Research Scientist.
