Half of these faces are of real people and the other half are AI-synthesized (i.e., deep fake). Can you tell which is which?
Although varied in their form and creation, deep fakes refer to AI-synthesized image, audio, or video. Deep fakes add to a long line of techniques for manipulating reality, but their introduction poses new risks because of the democratized access to what would have historically been the purview of Hollywood-style studios. In this talk, Farid will provide an overview of how deep fakes are created, how they are being used and misused, and if and how they can be perceptually and forensically distinguished from reality. Audience Q&A will follow.
Hany Farid is a Professor at the University of California, Berkeley with a joint appointment in the Department of Electrical Engineering and Computer Sciences and the School of Information. His research focuses on digital forensics, forensic science, misinformation, image analysis, and human perception. He is the recipient of an Alfred P. Sloan Fellowship and a John Simon Guggenheim Fellowship and is a Fellow of the National Academy of Inventors.
Sponsored by the IHC’s Too Much Information series and the IHC Idee Levitan Endowment
Free to attend; registration required to receive Zoom webinar attendance link