Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics

arXiv:2404.17867v1 Announce Type: new
Abstract: AI-generated content has accelerated the topic of media synthesis, particularly Deepfake, which can manipulate our portraits for positive or malicious purposes. Before releasing these threatening face images, one promising forensics solution is the injection of robust watermarks to track their own provenance. However, we argue that current watermarking models, originally devised for genuine images, may harm the deployed Deepfake detectors when directly applied to forged images, since the watermarks are prone to overlap with the …

abstract ai-generated content arxiv bugs cs.cv deepfake deepfake detectors detectors eess.iv face forensics generated however images media portraits positive provenance robust solution synthesis type watermarks