@inproceedings{hu-etal-2026-rethinking,
title = "Rethinking Reasoning: A Survey on Reasoning-based Backdoors in {LLM}s",
author = "Hu, Man and
Wu, Xinyi and
Suo, Zhufeng and
Feng, Jinbo and
Meng, Linghui and
Jia, Yanhao and
Luu, Anh Tuan and
Zhao, Shuai",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.863/",
pages = "17437--17456",
ISBN = "979-8-89176-395-1",
abstract = "With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. While reasoning enhances LLMs' performance on downstream tasks, it also introduces new threat vectors, as adversaries can leverage these capabilities to conduct backdoor attacks. Prior surveys provide broad overviews of backdoor attacks and reasoning security; however, a systematic survey focused on backdoor attacks and defenses against LLM reasoning is still absent. In this paper, we take the first step toward providing a comprehensive review of reasoning-based backdoor attacks in LLMs by analyzing their underlying mechanisms, methodological frameworks, and unresolved challenges. Specifically, we introduce a new taxonomy that offers a unified perspective for summarizing existing approaches, categorizing reasoning-based backdoor attacks into associative, passive, and active. We also summarize defenses against such attacks and discuss current challenges alongside future research directions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2026-rethinking">
<titleInfo>
<title>Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Man</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhufeng</namePart>
<namePart type="family">Suo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinbo</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linghui</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanhao</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="given">Tuan</namePart>
<namePart type="family">Luu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. While reasoning enhances LLMs’ performance on downstream tasks, it also introduces new threat vectors, as adversaries can leverage these capabilities to conduct backdoor attacks. Prior surveys provide broad overviews of backdoor attacks and reasoning security; however, a systematic survey focused on backdoor attacks and defenses against LLM reasoning is still absent. In this paper, we take the first step toward providing a comprehensive review of reasoning-based backdoor attacks in LLMs by analyzing their underlying mechanisms, methodological frameworks, and unresolved challenges. Specifically, we introduce a new taxonomy that offers a unified perspective for summarizing existing approaches, categorizing reasoning-based backdoor attacks into associative, passive, and active. We also summarize defenses against such attacks and discuss current challenges alongside future research directions.</abstract>
<identifier type="citekey">hu-etal-2026-rethinking</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.863/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>17437</start>
<end>17456</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
%A Hu, Man
%A Wu, Xinyi
%A Suo, Zhufeng
%A Feng, Jinbo
%A Meng, Linghui
%A Jia, Yanhao
%A Luu, Anh Tuan
%A Zhao, Shuai
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F hu-etal-2026-rethinking
%X With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. While reasoning enhances LLMs’ performance on downstream tasks, it also introduces new threat vectors, as adversaries can leverage these capabilities to conduct backdoor attacks. Prior surveys provide broad overviews of backdoor attacks and reasoning security; however, a systematic survey focused on backdoor attacks and defenses against LLM reasoning is still absent. In this paper, we take the first step toward providing a comprehensive review of reasoning-based backdoor attacks in LLMs by analyzing their underlying mechanisms, methodological frameworks, and unresolved challenges. Specifically, we introduce a new taxonomy that offers a unified perspective for summarizing existing approaches, categorizing reasoning-based backdoor attacks into associative, passive, and active. We also summarize defenses against such attacks and discuss current challenges alongside future research directions.
%U https://aclanthology.org/2026.findings-acl.863/
%P 17437-17456
Markdown (Informal)
[Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs](https://aclanthology.org/2026.findings-acl.863/) (Hu et al., Findings 2026)
ACL
- Man Hu, Xinyi Wu, Zhufeng Suo, Jinbo Feng, Linghui Meng, Yanhao Jia, Anh Tuan Luu, and Shuai Zhao. 2026. Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs. In Findings of the Association for Computational Linguistics: ACL 2026, pages 17437–17456, San Diego, California, United States. Association for Computational Linguistics.