@inproceedings{ren-etal-2024-subtle,
title = "Subtle Signatures, Strong Shields: Advancing Robust and Imperceptible Watermarking in Large Language Models",
author = "Ren, Yubing and
Guo, Ping and
Cao, Yanan and
Ma, Wei",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.327/",
doi = "10.18653/v1/2024.findings-acl.327",
pages = "5508--5519",
abstract = "The widespread adoption of Large Language Models (LLMs) has led to an increase in AI-generated text on the Internet, presenting a crucial challenge to differentiate AI-created content from human-written text. This challenge is critical to prevent issues of authenticity, trust, and potential copyright violations. Current research focuses on watermarking LLM-generated text, but traditional techniques struggle to balance robustness with text quality. We introduce a novel watermarking approach, Robust and Imperceptible Watermarking (RIW) for LLMs, which leverages token prior probabilities to improve detectability and maintain watermark imperceptibility. RIW methodically embeds watermarks by partitioning selected tokens into two distinct groups based on their prior probabilities and employing tailored strategies for each group. In the detection stage, the RIW method employs the {\textquoteleft}voted z-test' to provide a statistically robust framework to identify the presence of a watermark accurately. The effectiveness of RIW is evaluated across three key dimensions: success rate, text quality, and robustness against removal attacks. Our experimental results on various LLMs, including GPT2-XL, OPT-1.3B, and LLaMA2-7B, indicate that RIW surpasses existing models, and also exhibits increased robustness against various attacks and good imperceptibility, thus promoting the responsible use of LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ren-etal-2024-subtle">
<titleInfo>
<title>Subtle Signatures, Strong Shields: Advancing Robust and Imperceptible Watermarking in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yubing</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanan</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The widespread adoption of Large Language Models (LLMs) has led to an increase in AI-generated text on the Internet, presenting a crucial challenge to differentiate AI-created content from human-written text. This challenge is critical to prevent issues of authenticity, trust, and potential copyright violations. Current research focuses on watermarking LLM-generated text, but traditional techniques struggle to balance robustness with text quality. We introduce a novel watermarking approach, Robust and Imperceptible Watermarking (RIW) for LLMs, which leverages token prior probabilities to improve detectability and maintain watermark imperceptibility. RIW methodically embeds watermarks by partitioning selected tokens into two distinct groups based on their prior probabilities and employing tailored strategies for each group. In the detection stage, the RIW method employs the ‘voted z-test’ to provide a statistically robust framework to identify the presence of a watermark accurately. The effectiveness of RIW is evaluated across three key dimensions: success rate, text quality, and robustness against removal attacks. Our experimental results on various LLMs, including GPT2-XL, OPT-1.3B, and LLaMA2-7B, indicate that RIW surpasses existing models, and also exhibits increased robustness against various attacks and good imperceptibility, thus promoting the responsible use of LLMs.</abstract>
<identifier type="citekey">ren-etal-2024-subtle</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.327</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.327/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>5508</start>
<end>5519</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Subtle Signatures, Strong Shields: Advancing Robust and Imperceptible Watermarking in Large Language Models
%A Ren, Yubing
%A Guo, Ping
%A Cao, Yanan
%A Ma, Wei
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F ren-etal-2024-subtle
%X The widespread adoption of Large Language Models (LLMs) has led to an increase in AI-generated text on the Internet, presenting a crucial challenge to differentiate AI-created content from human-written text. This challenge is critical to prevent issues of authenticity, trust, and potential copyright violations. Current research focuses on watermarking LLM-generated text, but traditional techniques struggle to balance robustness with text quality. We introduce a novel watermarking approach, Robust and Imperceptible Watermarking (RIW) for LLMs, which leverages token prior probabilities to improve detectability and maintain watermark imperceptibility. RIW methodically embeds watermarks by partitioning selected tokens into two distinct groups based on their prior probabilities and employing tailored strategies for each group. In the detection stage, the RIW method employs the ‘voted z-test’ to provide a statistically robust framework to identify the presence of a watermark accurately. The effectiveness of RIW is evaluated across three key dimensions: success rate, text quality, and robustness against removal attacks. Our experimental results on various LLMs, including GPT2-XL, OPT-1.3B, and LLaMA2-7B, indicate that RIW surpasses existing models, and also exhibits increased robustness against various attacks and good imperceptibility, thus promoting the responsible use of LLMs.
%R 10.18653/v1/2024.findings-acl.327
%U https://aclanthology.org/2024.findings-acl.327/
%U https://doi.org/10.18653/v1/2024.findings-acl.327
%P 5508-5519
Markdown (Informal)
[Subtle Signatures, Strong Shields: Advancing Robust and Imperceptible Watermarking in Large Language Models](https://aclanthology.org/2024.findings-acl.327/) (Ren et al., Findings 2024)
ACL