@inproceedings{liu-etal-2024-shield,
title = "{SHIELD}: Evaluation and Defense Strategies for Copyright Compliance in {LLM} Text Generation",
author = "Liu, Xiaoze and
Sun, Ting and
Xu, Tianyang and
Wu, Feijie and
Wang, Cunxiang and
Wang, Xiaoqian and
Gao, Jing",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.98",
pages = "1640--1670",
abstract = "Large Language Models (LLMs) have transformed machine learning but raised significant legal concerns due to their potential to produce text that infringes on copyrights, resulting in several high-profile lawsuits. The legal landscape is struggling to keep pace with these rapid advancements, with ongoing debates about whether generated text might plagiarize copyrighted materials. Current LLMs may infringe on copyrights or overly restrict non-copyrighted texts, leading to these challenges: (i) the need for a comprehensive evaluation benchmark to assess copyright compliance from multiple aspects; (ii) evaluating robustness against safeguard bypassing attacks; and (iii) developing effective defenses targeted against the generation of copyrighted text.To tackle these challenges, we introduce a curated dataset to evaluate methods, test attack strategies, and propose a lightweight, real-time defense mechanism to prevent the generation of copyrighted text, ensuring the safe and lawful use of LLMs. Our experiments demonstrate that current LLMs frequently output copyrighted text, and that jailbreaking attacks can significantly increase the volume of copyrighted output. Our proposed defense mechanism substantially reduces the volume of copyrighted text generated by LLMs by effectively refusing malicious requests.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2024-shield">
<titleInfo>
<title>SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoze</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feijie</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cunxiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqian</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have transformed machine learning but raised significant legal concerns due to their potential to produce text that infringes on copyrights, resulting in several high-profile lawsuits. The legal landscape is struggling to keep pace with these rapid advancements, with ongoing debates about whether generated text might plagiarize copyrighted materials. Current LLMs may infringe on copyrights or overly restrict non-copyrighted texts, leading to these challenges: (i) the need for a comprehensive evaluation benchmark to assess copyright compliance from multiple aspects; (ii) evaluating robustness against safeguard bypassing attacks; and (iii) developing effective defenses targeted against the generation of copyrighted text.To tackle these challenges, we introduce a curated dataset to evaluate methods, test attack strategies, and propose a lightweight, real-time defense mechanism to prevent the generation of copyrighted text, ensuring the safe and lawful use of LLMs. Our experiments demonstrate that current LLMs frequently output copyrighted text, and that jailbreaking attacks can significantly increase the volume of copyrighted output. Our proposed defense mechanism substantially reduces the volume of copyrighted text generated by LLMs by effectively refusing malicious requests.</abstract>
<identifier type="citekey">liu-etal-2024-shield</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.98</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1640</start>
<end>1670</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation
%A Liu, Xiaoze
%A Sun, Ting
%A Xu, Tianyang
%A Wu, Feijie
%A Wang, Cunxiang
%A Wang, Xiaoqian
%A Gao, Jing
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F liu-etal-2024-shield
%X Large Language Models (LLMs) have transformed machine learning but raised significant legal concerns due to their potential to produce text that infringes on copyrights, resulting in several high-profile lawsuits. The legal landscape is struggling to keep pace with these rapid advancements, with ongoing debates about whether generated text might plagiarize copyrighted materials. Current LLMs may infringe on copyrights or overly restrict non-copyrighted texts, leading to these challenges: (i) the need for a comprehensive evaluation benchmark to assess copyright compliance from multiple aspects; (ii) evaluating robustness against safeguard bypassing attacks; and (iii) developing effective defenses targeted against the generation of copyrighted text.To tackle these challenges, we introduce a curated dataset to evaluate methods, test attack strategies, and propose a lightweight, real-time defense mechanism to prevent the generation of copyrighted text, ensuring the safe and lawful use of LLMs. Our experiments demonstrate that current LLMs frequently output copyrighted text, and that jailbreaking attacks can significantly increase the volume of copyrighted output. Our proposed defense mechanism substantially reduces the volume of copyrighted text generated by LLMs by effectively refusing malicious requests.
%U https://aclanthology.org/2024.emnlp-main.98
%P 1640-1670
Markdown (Informal)
[SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation](https://aclanthology.org/2024.emnlp-main.98) (Liu et al., EMNLP 2024)
ACL
- Xiaoze Liu, Ting Sun, Tianyang Xu, Feijie Wu, Cunxiang Wang, Xiaoqian Wang, and Jing Gao. 2024. SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1640–1670, Miami, Florida, USA. Association for Computational Linguistics.