Keywords:  AI and Machine Learning,


Learning Photo Forensics

Andrew Owens, Postdoctoral Researcher, Department of Electrical Engineering and Computer Sciences, UC Berkeley

Advances in photo editing and manipulation tools have made it significantly easier to create fake imagery. Learning to detect such manipulations, however, remains a challenging problem due to the lack of sufficient amounts of manipulated training data. We propose to address this problem by developing new, sample-efficient learning methods that can learn to detect fake images with minimal labeled training data.