Facebook scientists said they developed artificial intelligence software that not only identifies “deep fake” images but also figures out where they came from.
Deep Fakes are photos, videos or audio clips altered using artificial intelligence to appear authentic, which experts have warned can mislead or be completely false.
Facebook research scientists Tal Hassner and Xi Yin said their team worked with Michigan State University to create software that reverses engineers deep fake images to figure out how they were made and where they originated. They said in a post:
“Our method will facilitate deep face detection and tracking in real-world settings, where the deep fake image itself is often the only information detectors have to work with. This work will give researchers and practitioners tools to better investigate incidents of coordinated disinformation using deep fakes, as well as open up new directions for future research. Facebook’s new software runs deep fakes through a network to search for imperfections left during the manufacturing process, which the scientists say alter an image’s digital fingerprint. In digital photography, fingerprints are used to identify the digital camera used to produce an image. Similar to devise fingerprints, image fingerprints are unique patterns left on images… that can equally be used to identify the generative model that the image came from. Our research pushes the boundaries of understanding in deepfake detection.”
Microsoft last year unveiled software that can help spot deep fake photos or videos, adding to an arsenal of programs designed to fight the hard-to-detect images ahead of the US presidential election. The company’s Video Authenticator software analyzes an image for each frame of a video, looking for evidence of manipulation that could be invisible to the naked eye.