Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models

ePrint Report: Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models

Hanlin Zhang, Benjamin L. Edelman, Danilo Francati, Daniele Venturi, Giuseppe Ateniese, Boaz Barak

Watermarking generative models consists of planting a statistical signal (watermark) in a model’s output so that it can be later verified that the output was generated by the given model. A strong watermarking scheme satisfies the property that a computationally bounded attacker cannot erase the watermark without causing significant quality degradation. In this paper, …

barak eprint report generative generative models report signal verified watermarking watermarks