Evading deepfake detectors via adversarial statistical consistency

• المؤلفون الرئيسيون: HOU, Yang, GUO, Qing, HUANG, Yihao, XIE, Xiaofei, MA, Lei, ZHAO, Jianjun
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2023
• الموضوعات: degradation; deepfakes; frequency-domain analysis; closed box; detectors; forgery; pattern recognition; Graphics and Human Computer Interfaces
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/8230; https://ink.library.smu.edu.sg/context/sis_research/article/9233/viewcontent/evading_deepfake_detectors_va_adversarial_statistical_consistency.pdf

In recent years, as various realistic face forgery techniques known as DeepFake improves by leaps and bounds, more and more DeepFake detection techniques have been proposed. These methods typically rely on detecting statistical differences between natural (i.e., real) and DeepFake-generated images i...