A Semantic Invariant Robust Watermark for Large Language Models

arXiv:2310.06356v2 Announce Type: replace
Abstract: Watermark algorithms for large language models (LLMs) have achieved extremely high accuracy in detecting text generated by LLMs. Such algorithms typically involve adding extra watermark logits to the LLM's logits at each generation step. However, prior algorithms face a trade-off between attack robustness and security robustness. This is because the watermark logits for a token are determined by a certain number of preceding tokens; a small number leads to low security robustness, while a large …

arxiv cs.cl cs.cr language language models large semantic