@inproceedings{zhong-etal-2025-web,
title = "Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models",
author = "Zhong, Yisheng and
Wen, Yizhu and
Guo, Junfeng and
Kafai, Mehran and
Huang, Heng and
Guo, Hanqing and
Zhu, Zhuangdi",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.870/",
doi = "10.18653/v1/2025.emnlp-main.870",
pages = "17211--17224",
ISBN = "979-8-89176-332-6",
abstract = "The protection of cyber Intellectual Property (IP) such as web content is an increasingly critical concern. The rise of large language models (LLMs) with online retrieval capabilities enables convenient access to information but often undermines the rights of original content creators. As users increasingly rely on LLM-generated responses, they gradually diminish direct engagement with original information sources, which will significantly reduce the incentives for IP creators to contribute, and lead to a saturating cyberspace with more AI-generated content. In response, we propose a novel defense framework that empowers web content creators to safeguard their web-based IP from unauthorized LLM real-time extraction and redistribution by leveraging the semantic understanding capability of LLMs themselves. Our method follows principled motivations and effectively addresses an intractable black-box optimization problem. Real-world experiments demonstrated that our methods improve defense success rates from 2.5{\%} to 88.6{\%} on different LLMs, outperforming traditional defenses such as configuration-based restrictions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhong-etal-2025-web">
<titleInfo>
<title>Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yisheng</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yizhu</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junfeng</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehran</namePart>
<namePart type="family">Kafai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanqing</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuangdi</namePart>
<namePart type="family">Zhu</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>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>The protection of cyber Intellectual Property (IP) such as web content is an increasingly critical concern. The rise of large language models (LLMs) with online retrieval capabilities enables convenient access to information but often undermines the rights of original content creators. As users increasingly rely on LLM-generated responses, they gradually diminish direct engagement with original information sources, which will significantly reduce the incentives for IP creators to contribute, and lead to a saturating cyberspace with more AI-generated content. In response, we propose a novel defense framework that empowers web content creators to safeguard their web-based IP from unauthorized LLM real-time extraction and redistribution by leveraging the semantic understanding capability of LLMs themselves. Our method follows principled motivations and effectively addresses an intractable black-box optimization problem. Real-world experiments demonstrated that our methods improve defense success rates from 2.5% to 88.6% on different LLMs, outperforming traditional defenses such as configuration-based restrictions.</abstract>
<identifier type="citekey">zhong-etal-2025-web</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.870</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.870/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>17211</start>
<end>17224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models
%A Zhong, Yisheng
%A Wen, Yizhu
%A Guo, Junfeng
%A Kafai, Mehran
%A Huang, Heng
%A Guo, Hanqing
%A Zhu, Zhuangdi
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F zhong-etal-2025-web
%X The protection of cyber Intellectual Property (IP) such as web content is an increasingly critical concern. The rise of large language models (LLMs) with online retrieval capabilities enables convenient access to information but often undermines the rights of original content creators. As users increasingly rely on LLM-generated responses, they gradually diminish direct engagement with original information sources, which will significantly reduce the incentives for IP creators to contribute, and lead to a saturating cyberspace with more AI-generated content. In response, we propose a novel defense framework that empowers web content creators to safeguard their web-based IP from unauthorized LLM real-time extraction and redistribution by leveraging the semantic understanding capability of LLMs themselves. Our method follows principled motivations and effectively addresses an intractable black-box optimization problem. Real-world experiments demonstrated that our methods improve defense success rates from 2.5% to 88.6% on different LLMs, outperforming traditional defenses such as configuration-based restrictions.
%R 10.18653/v1/2025.emnlp-main.870
%U https://aclanthology.org/2025.emnlp-main.870/
%U https://doi.org/10.18653/v1/2025.emnlp-main.870
%P 17211-17224
Markdown (Informal)
[Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models](https://aclanthology.org/2025.emnlp-main.870/) (Zhong et al., EMNLP 2025)
ACL