@inproceedings{long-etal-2025-profiling,
title = "Profiling {LLM}{'}s Copyright Infringement Risks under Adversarial Persuasive Prompting",
author = "Long, Jikai and
Liu, Ming and
Chen, Xiusi and
Xu, Jialiang and
Li, Shenglan and
Xu, Zhaozhuo and
Zhang, Denghui",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.855/",
doi = "10.18653/v1/2025.findings-emnlp.855",
pages = "15799--15823",
ISBN = "979-8-89176-335-7",
abstract = "Large Language Models (LLMs) have demonstrated impressive capabilities in text generation but raise concerns regarding potential copyright infringement. While prior research has explored mitigation strategies like content filtering and alignment, the impact of adversarial persuasion techniques in eliciting copyrighted content remains underexplored. This paper investigates how structured persuasion strategies, including logical appeals, emotional framing, and compliance techniques, can be used to manipulate LLM outputs and potentially increase copyright risks. We introduce a structured persuasion workflow, incorporating query mutation, intention-preserving filtering, and few-shot prompting, to systematically analyze the influence of persuasive prompts on LLM responses. Through experiments on state-of-the-art LLMs, including GPT-4o-mini and Claude-3-haiku, we quantify the effectiveness of different persuasion techniques and assess their implications for AI safety. Our results highlight the vulnerabilities of LLMs to adversarial persuasion and provide empirical evidence of the increased risk of generating copyrighted content under such influence. We conclude with recommendations for strengthening model safeguards and future directions for enhancing LLM robustness against manipulation. Code is available at https://github.com/Rongite/Persuasion."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="long-etal-2025-profiling">
<titleInfo>
<title>Profiling LLM’s Copyright Infringement Risks under Adversarial Persuasive Prompting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jikai</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiusi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jialiang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shenglan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaozhuo</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denghui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have demonstrated impressive capabilities in text generation but raise concerns regarding potential copyright infringement. While prior research has explored mitigation strategies like content filtering and alignment, the impact of adversarial persuasion techniques in eliciting copyrighted content remains underexplored. This paper investigates how structured persuasion strategies, including logical appeals, emotional framing, and compliance techniques, can be used to manipulate LLM outputs and potentially increase copyright risks. We introduce a structured persuasion workflow, incorporating query mutation, intention-preserving filtering, and few-shot prompting, to systematically analyze the influence of persuasive prompts on LLM responses. Through experiments on state-of-the-art LLMs, including GPT-4o-mini and Claude-3-haiku, we quantify the effectiveness of different persuasion techniques and assess their implications for AI safety. Our results highlight the vulnerabilities of LLMs to adversarial persuasion and provide empirical evidence of the increased risk of generating copyrighted content under such influence. We conclude with recommendations for strengthening model safeguards and future directions for enhancing LLM robustness against manipulation. Code is available at https://github.com/Rongite/Persuasion.</abstract>
<identifier type="citekey">long-etal-2025-profiling</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.855</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.855/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>15799</start>
<end>15823</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Profiling LLM’s Copyright Infringement Risks under Adversarial Persuasive Prompting
%A Long, Jikai
%A Liu, Ming
%A Chen, Xiusi
%A Xu, Jialiang
%A Li, Shenglan
%A Xu, Zhaozhuo
%A Zhang, Denghui
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F long-etal-2025-profiling
%X Large Language Models (LLMs) have demonstrated impressive capabilities in text generation but raise concerns regarding potential copyright infringement. While prior research has explored mitigation strategies like content filtering and alignment, the impact of adversarial persuasion techniques in eliciting copyrighted content remains underexplored. This paper investigates how structured persuasion strategies, including logical appeals, emotional framing, and compliance techniques, can be used to manipulate LLM outputs and potentially increase copyright risks. We introduce a structured persuasion workflow, incorporating query mutation, intention-preserving filtering, and few-shot prompting, to systematically analyze the influence of persuasive prompts on LLM responses. Through experiments on state-of-the-art LLMs, including GPT-4o-mini and Claude-3-haiku, we quantify the effectiveness of different persuasion techniques and assess their implications for AI safety. Our results highlight the vulnerabilities of LLMs to adversarial persuasion and provide empirical evidence of the increased risk of generating copyrighted content under such influence. We conclude with recommendations for strengthening model safeguards and future directions for enhancing LLM robustness against manipulation. Code is available at https://github.com/Rongite/Persuasion.
%R 10.18653/v1/2025.findings-emnlp.855
%U https://aclanthology.org/2025.findings-emnlp.855/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.855
%P 15799-15823
Markdown (Informal)
[Profiling LLM’s Copyright Infringement Risks under Adversarial Persuasive Prompting](https://aclanthology.org/2025.findings-emnlp.855/) (Long et al., Findings 2025)
ACL