PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators. (arXiv:2304.07361v2 [cs.LG] UPDATED)

Deepfakes refer to content synthesized using deep generators, which, when
misused, have the potential to erode trust in digital media. Synthesizing
high-quality deepfakes requires access to large and complex generators only a
few entities can train and provide. The threat is malicious users that exploit
access to the provided model and generate harmful deepfakes without risking
detection. Watermarking makes deepfakes detectable by embedding an identifiable
code into the generator that is later extractable from its generated images. We
propose Pivotal …

access deepfakes digital digital media entities exploit high large malicious media quality synthesized threat train trust watermarking