7 citations · 12 across the 7 of their papers we have counts for
3 papers · 1 filter
Watermarking Makes Language Models Radioactive
Tom Sander, Pierre Fernandez, Alain Durmus +2
We investigate the radioactivity of text generated by large language models (LLM), i.e. whether it is possible to detect that such synthetic input was used to train a subsequent LL…
Functional Invariants to Watermark Large Transformers
Pierre Fernandez, Guillaume Couairon, Teddy Furon +1
The rapid growth of transformer-based models increases the concerns about their integrity and ownership insurance. Watermarking addresses this issue by embedding a unique identifie…
FBI: Fingerprinting models with Benign Inputs
Thibault Maho, Teddy Furon, Erwan Le Merrer
Recent advances in the fingerprinting of deep neural networks detect instances of models, placed in a black-box interaction scheme. Inputs used by the fingerprinting protocols are…