@inproceedings{ti-etal-2025-towards,
title = "Towards Reverse Engineering of Language Models: A Survey",
author = "Ti, Xinpeng and
Ye, Wentao and
Zhang, Zhifang and
Zhao, Junbo and
Yao, Chang and
Feng, Lei and
Wang, Haobo",
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.395/",
pages = "7483--7502",
ISBN = "979-8-89176-335-7",
abstract = "With the continuous development of language models and the widespread availability of various types of accessible interfaces, large language models (LLMs) have been applied to an increasing number of fields. However, due to the vast amounts of data and computational resources required for model development, protecting the model{'}s parameters and training data has become an urgent and crucial concern. Due to the revolutionary training and application paradigms of LLMs, many new attacks on language models have emerged in recent years. In this paper, we define these attacks as ``reverse engineering'' (RE) techniques on LMs and aim to provide an in-depth analysis of reverse engineering of language models. We illustrate various methods of reverse engineering applied to different aspects of a model, while also providing an introduction to existing protective strategies. On the one hand, it demonstrates the vulnerabilities of even black box models to different types of attacks; on the other hand, it offers a more holistic perspective for the development of new protective strategies for models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ti-etal-2025-towards">
<titleInfo>
<title>Towards Reverse Engineering of Language Models: A Survey</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinpeng</namePart>
<namePart type="family">Ti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wentao</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhifang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junbo</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haobo</namePart>
<namePart type="family">Wang</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>With the continuous development of language models and the widespread availability of various types of accessible interfaces, large language models (LLMs) have been applied to an increasing number of fields. However, due to the vast amounts of data and computational resources required for model development, protecting the model’s parameters and training data has become an urgent and crucial concern. Due to the revolutionary training and application paradigms of LLMs, many new attacks on language models have emerged in recent years. In this paper, we define these attacks as “reverse engineering” (RE) techniques on LMs and aim to provide an in-depth analysis of reverse engineering of language models. We illustrate various methods of reverse engineering applied to different aspects of a model, while also providing an introduction to existing protective strategies. On the one hand, it demonstrates the vulnerabilities of even black box models to different types of attacks; on the other hand, it offers a more holistic perspective for the development of new protective strategies for models.</abstract>
<identifier type="citekey">ti-etal-2025-towards</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.395/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>7483</start>
<end>7502</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Reverse Engineering of Language Models: A Survey
%A Ti, Xinpeng
%A Ye, Wentao
%A Zhang, Zhifang
%A Zhao, Junbo
%A Yao, Chang
%A Feng, Lei
%A Wang, Haobo
%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 ti-etal-2025-towards
%X With the continuous development of language models and the widespread availability of various types of accessible interfaces, large language models (LLMs) have been applied to an increasing number of fields. However, due to the vast amounts of data and computational resources required for model development, protecting the model’s parameters and training data has become an urgent and crucial concern. Due to the revolutionary training and application paradigms of LLMs, many new attacks on language models have emerged in recent years. In this paper, we define these attacks as “reverse engineering” (RE) techniques on LMs and aim to provide an in-depth analysis of reverse engineering of language models. We illustrate various methods of reverse engineering applied to different aspects of a model, while also providing an introduction to existing protective strategies. On the one hand, it demonstrates the vulnerabilities of even black box models to different types of attacks; on the other hand, it offers a more holistic perspective for the development of new protective strategies for models.
%U https://aclanthology.org/2025.findings-emnlp.395/
%P 7483-7502
Markdown (Informal)
[Towards Reverse Engineering of Language Models: A Survey](https://aclanthology.org/2025.findings-emnlp.395/) (Ti et al., Findings 2025)
ACL
- Xinpeng Ti, Wentao Ye, Zhifang Zhang, Junbo Zhao, Chang Yao, Lei Feng, and Haobo Wang. 2025. Towards Reverse Engineering of Language Models: A Survey. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 7483–7502, Suzhou, China. Association for Computational Linguistics.