Gloaguen, Thibaud
- Black-Box Detection of Language Model Watermarks
2024/05/28 by Gloaguen Thibaud, Jovanović Nikola, Gloaguen, Thibaud +5 · 8 citations
Computer Science · #Cryptography and Security (cs.CR) #Digital and Cyber Forensics #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Machine Learning (cs.LG) #Natural Language Processing Techniques
- Towards Watermarking of Open-Source LLMs
2025/02/14 by Gloaguen, Thibaud, Jovanović, Nikola, Staab, Robin +1 · 8 citations
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- LLM Fingerprinting via Semantically Conditioned Watermarks
2025/05/22 by Thibaud Gloaguen, Robin Staab, Gloaguen, Thibaud +5 · 3 citations
Computer Science · #Advanced Steganography and Watermarking Techniques #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Internet Traffic Analysis and Secure E-voting #Machine Learning (cs.LG)
- Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
2025/05/22 by Thibaud Gloaguen, Mark Vero, Gloaguen, Thibaud +5 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling