Saved in:
Bibliographic Details
Main Authors: Nagatsuka, Koichi, Morishita, Terufumi, Sogawa, Yasuhiro
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.17308
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909654500507648
author Nagatsuka, Koichi
Morishita, Terufumi
Sogawa, Yasuhiro
author_facet Nagatsuka, Koichi
Morishita, Terufumi
Sogawa, Yasuhiro
contents The rapid advancement of large language models (LLMs) has raised concerns regarding their potential misuse, particularly in generating fake news and misinformation. To address these risks, watermarking techniques for autoregressive language models have emerged as a promising means for detecting LLM-generated text. Existing methods typically embed a watermark by increasing the probabilities of tokens within a group selected according to a single secret key. However, this approach suffers from a critical limitation: if the key is leaked, it becomes impossible to trace the text's provenance or attribute authorship. To overcome this vulnerability, we propose a novel nested watermarking scheme that embeds two distinct watermarks into the generated text using two independent keys. This design enables reliable authorship identification even in the event that one key is compromised. Experimental results demonstrate that our method achieves high detection accuracy for both watermarks while maintaining the fluency and overall quality of the generated text.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17308
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Nested Watermark for Large Language Models
Nagatsuka, Koichi
Morishita, Terufumi
Sogawa, Yasuhiro
Cryptography and Security
The rapid advancement of large language models (LLMs) has raised concerns regarding their potential misuse, particularly in generating fake news and misinformation. To address these risks, watermarking techniques for autoregressive language models have emerged as a promising means for detecting LLM-generated text. Existing methods typically embed a watermark by increasing the probabilities of tokens within a group selected according to a single secret key. However, this approach suffers from a critical limitation: if the key is leaked, it becomes impossible to trace the text's provenance or attribute authorship. To overcome this vulnerability, we propose a novel nested watermarking scheme that embeds two distinct watermarks into the generated text using two independent keys. This design enables reliable authorship identification even in the event that one key is compromised. Experimental results demonstrate that our method achieves high detection accuracy for both watermarks while maintaining the fluency and overall quality of the generated text.
title A Nested Watermark for Large Language Models
topic Cryptography and Security
url https://arxiv.org/abs/2506.17308