@inproceedings{wang-etal-2026-cpf,
title = "{CPF}: Concept-based Probabilistic Fingerprinting for Copyright Protection in Multimodal Large Language Models",
author = "Wang, Xinghao and
Zheng, Xiaofan and
Peng, Peng and
Luo, Minnan",
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.2476/",
doi = "10.18653/2026.findings-emnlp.2476",
pages = "53288--53304",
ISBN = "979-8-89176-462-0",
abstract = "With the widespread deployment and application of Multimodal Large Language Models (MLLMs), disputes over model ownership have become increasingly frequent, raising serious concerns about intellectual property protection in black-box scenarios. Existing techniques primarily embed copyright information into models through backdoor or adversarial attacks, triggering abnormal outputs on specific inputs for verification. However, we find that such methods exhibit limited robustness after post-processing operations such as fine-tuning, pruning, and model merging. To address this, we propose Concept-based Probabilistic Fingerprinting (CPF). CPF selects a visual concept as the fingerprint trigger, embeds statistical watermark signals in concept-related multimodal conversations, and migrates the watermarked distribution to the original model through self-distillation. It further employs cross-concept similarity screening to construct a regularization constraint, ensuring the fingerprint is activated only on the target concept. CPF does not trigger semantically irrelevant abnormal outputs, nor does it rely on fixed inputs as triggers. Experimental results demonstrate that CPF maintains stable fingerprint detectability across diverse scenarios while exhibiting strong robustness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-cpf">
<titleInfo>
<title>CPF: Concept-based Probabilistic Fingerprinting for Copyright Protection in Multimodal Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinghao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaofan</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minnan</namePart>
<namePart type="family">Luo</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>With the widespread deployment and application of Multimodal Large Language Models (MLLMs), disputes over model ownership have become increasingly frequent, raising serious concerns about intellectual property protection in black-box scenarios. Existing techniques primarily embed copyright information into models through backdoor or adversarial attacks, triggering abnormal outputs on specific inputs for verification. However, we find that such methods exhibit limited robustness after post-processing operations such as fine-tuning, pruning, and model merging. To address this, we propose Concept-based Probabilistic Fingerprinting (CPF). CPF selects a visual concept as the fingerprint trigger, embeds statistical watermark signals in concept-related multimodal conversations, and migrates the watermarked distribution to the original model through self-distillation. It further employs cross-concept similarity screening to construct a regularization constraint, ensuring the fingerprint is activated only on the target concept. CPF does not trigger semantically irrelevant abnormal outputs, nor does it rely on fixed inputs as triggers. Experimental results demonstrate that CPF maintains stable fingerprint detectability across diverse scenarios while exhibiting strong robustness.</abstract>
<identifier type="citekey">wang-etal-2026-cpf</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.2476</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2476/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>53288</start>
<end>53304</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CPF: Concept-based Probabilistic Fingerprinting for Copyright Protection in Multimodal Large Language Models
%A Wang, Xinghao
%A Zheng, Xiaofan
%A Peng, Peng
%A Luo, Minnan
%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 wang-etal-2026-cpf
%X With the widespread deployment and application of Multimodal Large Language Models (MLLMs), disputes over model ownership have become increasingly frequent, raising serious concerns about intellectual property protection in black-box scenarios. Existing techniques primarily embed copyright information into models through backdoor or adversarial attacks, triggering abnormal outputs on specific inputs for verification. However, we find that such methods exhibit limited robustness after post-processing operations such as fine-tuning, pruning, and model merging. To address this, we propose Concept-based Probabilistic Fingerprinting (CPF). CPF selects a visual concept as the fingerprint trigger, embeds statistical watermark signals in concept-related multimodal conversations, and migrates the watermarked distribution to the original model through self-distillation. It further employs cross-concept similarity screening to construct a regularization constraint, ensuring the fingerprint is activated only on the target concept. CPF does not trigger semantically irrelevant abnormal outputs, nor does it rely on fixed inputs as triggers. Experimental results demonstrate that CPF maintains stable fingerprint detectability across diverse scenarios while exhibiting strong robustness.
%R 10.18653/2026.findings-emnlp.2476
%U https://aclanthology.org/2026.findings-emnlp.2476/
%U https://doi.org/10.18653/2026.findings-emnlp.2476
%P 53288-53304
Markdown (Informal)
[CPF: Concept-based Probabilistic Fingerprinting for Copyright Protection in Multimodal Large Language Models](https://aclanthology.org/2026.findings-emnlp.2476/) (Wang et al., Findings 2026)
ACL