Cryptography and Security

Watermarking Makes Language Models Radioactive

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 LLM. Current methods like membership inference or active IP protection…

Tom Sander, Pierre Fernandez, Alain Durmus, Matthijs Douze, Teddy Furon

NeurIPS 2024 - 38th Conference on Neural Information Processing Systems - 2024