FakePolisher: Making deepfakes more detection-evasive by shallow reconstruction

• Main Authors: HUANG, Yihao, JUEFEI-XU, Felix, WANG, Run, GUO, Qing, MA, Lei, XIE, Xiaofei, LI, Jianwen, MIAO, Weikai, LIU, Yang, PU, Geguang
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Computer vision; DeepFake; Shallow Reconstruction; Graphics and Human Computer Interfaces; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/7078; https://ink.library.smu.edu.sg/context/sis_research/article/8081/viewcontent/3394171.3413732.pdf
• Institution: Singapore Management University

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...