Skip to content

Author

Hady ElSahar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Watermark Basins: Black-Box Detection of Distilled LLMs

Proprietary language models and their reasoning traces are vulnerable to API-based distillation, where an adversary trains a student model on the teacher model's outputs. To obtain evidence of distillation, model providers can watermark the teacher's outputs, aiming to leave a radioactive signal in the student's output...

Hong-Yan Chang, Hady ElSahar, Tom Sander et al. · 0 citations
#artificial intelligence Preprint Oct 2026

TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races

We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain watermarked with the same keys, and the acceptance rate is unchanged. It also preserves output diversity and adds no measurable inference latency. Its...

Tom Sander, Pierre Fernandez, Itai Gat et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.