Thibaud Gloaguen

According to our database, Thibaud Gloaguen authored at least 8 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

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

Kazuki Egashira, Robin Staab, Thibaud Gloaguen, Mark Vero, Martin T. Vechev

CoRR, October, 2025

Watermarking Diffusion Language Models.

Thibaud Gloaguen, Robin Staab, Nikola Jovanovic, Martin T. Vechev

CoRR, September, 2025

Robust LLM Fingerprinting via Domain-Specific Watermarks.

Thibaud Gloaguen, Robin Staab, Nikola Jovanovic, Martin T. Vechev

CoRR, May, 2025

Finetuning-Activated Backdoors in LLMs.

Thibaud Gloaguen, Mark Vero, Robin Staab, Martin T. Vechev

CoRR, May, 2025

Towards Watermarking of Open-Source LLMs.

Thibaud Gloaguen, Nikola Jovanovic, Robin Staab, Martin T. Vechev

CoRR, February, 2025

Discovering Spoofing Attempts on Language Model Watermarks.

Thibaud Gloaguen, Nikola Jovanovic, Robin Staab, Martin T. Vechev

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Black-Box Detection of Language Model Watermarks.

Thibaud Gloaguen, Nikola Jovanovic, Robin Staab, Martin T. Vechev

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Discovering Clues of Spoofed LM Watermarks.

Thibaud Gloaguen, Nikola Jovanovic, Robin Staab, Martin T. Vechev

CoRR, 2024