FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction
Yihao Huang, Felix Juefei-Xu, Run Wang, Qing Guo, Lei Ma, Xiaofei Xie, Jianwen Li, Weikai Miao, Yang Liu, Geguang Pu
Abstract
At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image. Such artifact patterns can be easily exploited (by recent methods) for difference detection of real and GAN-synthesized images. However, the existing detection methods put much emphasis on the artifact patterns, which can become futile if such artifact patterns were reduced.
Topics & Concepts
Artifact (error)UpsamplingComputer scienceArtificial intelligenceImperfectComputer visionMoment (physics)Emphasis (telecommunications)Image (mathematics)Pattern recognition (psychology)TelecommunicationsLinguisticsClassical mechanicsPhilosophyPhysicsDigital Media Forensic DetectionGenerative Adversarial Networks and Image SynthesisAdvanced Image Processing Techniques