@inproceedings{li-etal-2025-clever,
title = "{CL}e{V}e{R}: Multi-modal Contrastive Learning for Vulnerability Code Representation",
author = "Li, Jiayuan and
Cui, Lei and
Zhao, Sen and
Yang, Yun and
Li, Lun and
Zhu, Hongsong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.414/",
doi = "10.18653/v1/2025.findings-acl.414",
pages = "7940--7951",
ISBN = "979-8-89176-256-5",
abstract = "Automated vulnerability detection has become increasingly important. Many existing methods utilize deep learning models to obtain code representations for vulnerability detection. However, these approaches predominantly capture the overall semantics of the code rather than its intrinsic vulnerability-specific semantics. To address this issue, we propose CLeVeR, the first approach that leverages contrastive learning to generate precise vulnerability code representations under the supervision of vulnerability descriptions. Specifically, we introduce an Adapter, a Representation Refinement module, and a Description Simulator to mitigate the challenges of semantic misalignment and imbalance between code and descriptions, and input data inconsistency between pre-training and fine-tuning stages, respectively. For vulnerability detection and classification tasks, CLeVeR achieves F1 scores of 72.82{\%} (real-world dataset) and 80.34{\%}, outperforming state-of-the-art methods (SOTAs) by 11.85{\%} and 13.61{\%}. Additionally, CLeVeR also outperforms SOTAs in zero-shot inference, demonstrating the transferability of its generated vulnerability code representations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-clever">
<titleInfo>
<title>CLeVeR: Multi-modal Contrastive Learning for Vulnerability Code Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiayuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongsong</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Automated vulnerability detection has become increasingly important. Many existing methods utilize deep learning models to obtain code representations for vulnerability detection. However, these approaches predominantly capture the overall semantics of the code rather than its intrinsic vulnerability-specific semantics. To address this issue, we propose CLeVeR, the first approach that leverages contrastive learning to generate precise vulnerability code representations under the supervision of vulnerability descriptions. Specifically, we introduce an Adapter, a Representation Refinement module, and a Description Simulator to mitigate the challenges of semantic misalignment and imbalance between code and descriptions, and input data inconsistency between pre-training and fine-tuning stages, respectively. For vulnerability detection and classification tasks, CLeVeR achieves F1 scores of 72.82% (real-world dataset) and 80.34%, outperforming state-of-the-art methods (SOTAs) by 11.85% and 13.61%. Additionally, CLeVeR also outperforms SOTAs in zero-shot inference, demonstrating the transferability of its generated vulnerability code representations.</abstract>
<identifier type="citekey">li-etal-2025-clever</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.414</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.414/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>7940</start>
<end>7951</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLeVeR: Multi-modal Contrastive Learning for Vulnerability Code Representation
%A Li, Jiayuan
%A Cui, Lei
%A Zhao, Sen
%A Yang, Yun
%A Li, Lun
%A Zhu, Hongsong
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F li-etal-2025-clever
%X Automated vulnerability detection has become increasingly important. Many existing methods utilize deep learning models to obtain code representations for vulnerability detection. However, these approaches predominantly capture the overall semantics of the code rather than its intrinsic vulnerability-specific semantics. To address this issue, we propose CLeVeR, the first approach that leverages contrastive learning to generate precise vulnerability code representations under the supervision of vulnerability descriptions. Specifically, we introduce an Adapter, a Representation Refinement module, and a Description Simulator to mitigate the challenges of semantic misalignment and imbalance between code and descriptions, and input data inconsistency between pre-training and fine-tuning stages, respectively. For vulnerability detection and classification tasks, CLeVeR achieves F1 scores of 72.82% (real-world dataset) and 80.34%, outperforming state-of-the-art methods (SOTAs) by 11.85% and 13.61%. Additionally, CLeVeR also outperforms SOTAs in zero-shot inference, demonstrating the transferability of its generated vulnerability code representations.
%R 10.18653/v1/2025.findings-acl.414
%U https://aclanthology.org/2025.findings-acl.414/
%U https://doi.org/10.18653/v1/2025.findings-acl.414
%P 7940-7951
Markdown (Informal)
[CLeVeR: Multi-modal Contrastive Learning for Vulnerability Code Representation](https://aclanthology.org/2025.findings-acl.414/) (Li et al., Findings 2025)
ACL