3 accepted papers
This paper introduces a novel watermarking method for diffusion models. It is based on guiding the diffusion process using the gradient computed from any off-the-shelf watermark decoder. The gradient is guided further using different image augmentations, increasing robustness to attacks against whic…
The omnipresence of generated content has led to an increasing need of multimedia content traceability. Water-marking techniques have been proven to provide both detection guarantees and robustness. However, widespread use of such methods would require disclosing the watermark detector to the public…
Watermarking is a technical means to dissuade malfeasant usage of Large Language Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that enjoys high detectability while sustaining the quality of the generated text of the original LLM. Its new design leaves the LLM untouched…