activity
20242026
collaborators

6 papers

cs.CR2026

A Unified Framework for LLM Watermarks

Thibaud Gloaguen, Robin Staab, Nikola Jovanović +1

LLM watermarks allow tracing AI-generated texts by inserting a detectable signal into their generated content. Recent works have proposed a wide range of watermarking algorithms, e…

cs.LG2025

Fewer Weights, More Problems: A Practical Attack on LLM Pruning

Kazuki Egashira, Robin Staab, Thibaud Gloaguen +2

Model pruning, i.e., removing a subset of model weights, has become a prominent approach to reducing the memory footprint of large language models (LLMs) during inference. Notably,…

cs.LG2025

Watermarking Diffusion Language Models

Thibaud Gloaguen, Robin Staab, Nikola Jovanović +1

We introduce the first watermark tailored for diffusion language models (DLMs), an emergent LLM paradigm able to generate tokens in arbitrary order, in contrast to standard autoreg…

cs.CR2025

LLM Fingerprinting via Semantically Conditioned Watermarks

Thibaud Gloaguen, Robin Staab, Nikola Jovanović +1

Most LLM fingerprinting methods teach the model to respond to a few fixed queries with predefined atypical responses (keys). This memorization often does not survive common deploym…

cs.CR2025

Towards Watermarking of Open-Source LLMs

Thibaud Gloaguen, Nikola Jovanović, Robin Staab +1

While watermarks for closed LLMs have matured and have been included in large-scale deployments, these methods are not applicable to open-source models, which allow users full cont…

cs.CR2024

Discovering Spoofing Attempts on Language Model Watermarks

Thibaud Gloaguen, Nikola Jovanović, Robin Staab +1

LLM watermarks stand out as a promising way to attribute ownership of LLM-generated text. One threat to watermark credibility comes from spoofing attacks, where an unauthorized thi…