New Scientist quoted Siwei Lyu about new Deepfake detection technique: “Up to this point, we have not seen a single example of deepfake generation algorithms that can create realistic human hands and demonstrate the flexibility and gestures of a real human being,” says Lyu.
A deepfake detector designed to identify unique facial expressions and hand gestures could spot manipulated videos of world leaders such as Volodymyr Zelenskyy and Vladimir Putin. The new deepfake detector was developed by Hany Farid of UC Berkeley with Matyáš Boháček at Johannes Kepler Gymnasium in the Czech Republic. [Read Article]
Farid was Lyu’s doctoral research advisor and Lyu was involved in the research upon which this new deepfake detector is built. That previous research involved training a system to detect deepfake faces and head movements of world leaders.
Lyu is Co-Director of the Center for Information Integrity (CII) and Director of the Media Forensics Lab (MDFL), both at UB. Through the MDFL, Lyu maintains an open platform integrating state-of-the-art deepfake detection methods called “DeepFake-o-meter.” Through this platform, you can upload a video and receive an analysis of the likelihood that it has been manipulated.