@inproceedings{hong-etal-2026-cot,
title = "{C}o{T}-Lock: Embedding Logic Fingerprints into the Chain-of-Thought of Large Reasoning Models",
author = "Hong, Jiaxin and
Yu, Hongyao and
Fang, Hao and
Gao, Kuofeng and
Peng, Yuxin and
Chen, Bin and
Qi, Shuhan and
Wang, Xuan",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.847/",
pages = "17947--17969",
ISBN = "979-8-89176-462-0",
abstract = "Large Reasoning Models (LRMs) are valuable intellectual property due to their substantial training and alignment costs, creating a need for reliable ownership verification under black-box access, where a verifier can only query a suspect model and inspect its returned output. Existing trigger{--}response fingerprints are easy to test but are often weakly coupled with Chain-of-Thought (CoT) reasoning and can be fragile under paraphrasing or post-hoc model modifications. We propose CoT-Lock, a reasoning-mediated fingerprinting framework that casts ownership verification as a structured conflict-resolution task. CoT-Lock constructs verification queries in which a default semantic constraint is superseded only by a higher-priority meta-override rule, training the model to resolve fingerprint activation through priority-based arbitration. Our primary ownership test is output-only on confidential held-out probes; when reasoning traces are visible, trace-level verification further checks the expected arbitration process. Experiments on representative reasoning architectures show that CoT-Lock achieves stable black-box verification while preserving reasoning ability with minimal performance degradation, low false positives, and improved robustness against paraphrasing, fine-tuning, pruning, and quantization. Our code is available at https://github.com/acang425/CoT-Lock."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hong-etal-2026-cot">
<titleInfo>
<title>CoT-Lock: Embedding Logic Fingerprints into the Chain-of-Thought of Large Reasoning Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuofeng</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxin</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuhan</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large Reasoning Models (LRMs) are valuable intellectual property due to their substantial training and alignment costs, creating a need for reliable ownership verification under black-box access, where a verifier can only query a suspect model and inspect its returned output. Existing trigger–response fingerprints are easy to test but are often weakly coupled with Chain-of-Thought (CoT) reasoning and can be fragile under paraphrasing or post-hoc model modifications. We propose CoT-Lock, a reasoning-mediated fingerprinting framework that casts ownership verification as a structured conflict-resolution task. CoT-Lock constructs verification queries in which a default semantic constraint is superseded only by a higher-priority meta-override rule, training the model to resolve fingerprint activation through priority-based arbitration. Our primary ownership test is output-only on confidential held-out probes; when reasoning traces are visible, trace-level verification further checks the expected arbitration process. Experiments on representative reasoning architectures show that CoT-Lock achieves stable black-box verification while preserving reasoning ability with minimal performance degradation, low false positives, and improved robustness against paraphrasing, fine-tuning, pruning, and quantization. Our code is available at https://github.com/acang425/CoT-Lock.</abstract>
<identifier type="citekey">hong-etal-2026-cot</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.847/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>17947</start>
<end>17969</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoT-Lock: Embedding Logic Fingerprints into the Chain-of-Thought of Large Reasoning Models
%A Hong, Jiaxin
%A Yu, Hongyao
%A Fang, Hao
%A Gao, Kuofeng
%A Peng, Yuxin
%A Chen, Bin
%A Qi, Shuhan
%A Wang, Xuan
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F hong-etal-2026-cot
%X Large Reasoning Models (LRMs) are valuable intellectual property due to their substantial training and alignment costs, creating a need for reliable ownership verification under black-box access, where a verifier can only query a suspect model and inspect its returned output. Existing trigger–response fingerprints are easy to test but are often weakly coupled with Chain-of-Thought (CoT) reasoning and can be fragile under paraphrasing or post-hoc model modifications. We propose CoT-Lock, a reasoning-mediated fingerprinting framework that casts ownership verification as a structured conflict-resolution task. CoT-Lock constructs verification queries in which a default semantic constraint is superseded only by a higher-priority meta-override rule, training the model to resolve fingerprint activation through priority-based arbitration. Our primary ownership test is output-only on confidential held-out probes; when reasoning traces are visible, trace-level verification further checks the expected arbitration process. Experiments on representative reasoning architectures show that CoT-Lock achieves stable black-box verification while preserving reasoning ability with minimal performance degradation, low false positives, and improved robustness against paraphrasing, fine-tuning, pruning, and quantization. Our code is available at https://github.com/acang425/CoT-Lock.
%U https://aclanthology.org/2026.findings-emnlp.847/
%P 17947-17969
Markdown (Informal)
[CoT-Lock: Embedding Logic Fingerprints into the Chain-of-Thought of Large Reasoning Models](https://aclanthology.org/2026.findings-emnlp.847/) (Hong et al., Findings 2026)
ACL
- Jiaxin Hong, Hongyao Yu, Hao Fang, Kuofeng Gao, Yuxin Peng, Bin Chen, Shuhan Qi, and Xuan Wang. 2026. CoT-Lock: Embedding Logic Fingerprints into the Chain-of-Thought of Large Reasoning Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 17947–17969, Budapest, Hungary. Association for Computational Linguistics.