ACL Findings2025
Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data
Xin-Cheng Wen, Yijun Yang, Cuiyun Gao, Yang Xiao, Deheng Ye
摘要
Large language models (LLMs) demonstrate considerable proficiency in numerous codingrelated tasks; however, their capabilities in detecting software vulnerabilities remain limited. This limitation primarily stems from two factors: (1) the absence of reasoning data related to vulnerabilities, which hinders the models' ability to capture underlying vulnerability patterns; and (2) their focus on learning semantic representations rather than the reason behind them, thus failing to recognize semantically similar vulnerability samples. Furthermore, the development of LLMs specialized in vulnerability detection is challenging, particularly in environments characterized by the scarcity of high-quality datasets. In this paper, we propose a novel framework ReVD that excels at mining vulnerability patterns through reasoning data synthesizing and vulnerability-specific preference optimization. Specifically, we construct forward and backward reasoning processes for vulnerability and corresponding fixed code, ensuring the synthesis of high-quality reasoning data. Moreover, we design the triplet supervised fine-tuning followed by curriculum online preference optimization for enabling ReVD to better understand vulnerability patterns. The extensive experiments conducted on PrimeVul and SVEN datasets demonstrate that ReVD sets new state-of-the-art for LLM-based software vulnerability detection, e.g., 12.24%-22.77% improvement in the accuracy. The source code and data are available at https: //github.com/Xin-Cheng-Wen/PO4Vul.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 4 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
- Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation 引用了 Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Vul-R2: A Reasoning LLM for Automated Vulnerability Repair 引用了 Data Quality for Software Vulnerability Datasets
- Repo2Run: Automated Building Executable Environment for Code Repository at Scale 引用了 Vul-R2: A Reasoning LLM for Automated Vulnerability Repair
- SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning 引用了 Vul-R2: A Reasoning LLM for Automated Vulnerability Repair
- Data Quality for Software Vulnerability Datasets 引用了 CodeBERT: A Pre-Trained Model for Programming and Natural Languages
引用它的顶会 Paper4
- Repo2Run: Automated Building Executable Environment for Code Repository at ScaleRuida Hu, Chao Peng, Xinchen Wang, Junjielong Xu 等NeurIPS 2025 · 49 次引用
- Vul-R2: A Reasoning LLM for Automated Vulnerability RepairXin-Cheng Wen, Zirui Lin, Yijun Yang, Cuiyun Gao 等ASE 2025 · 1 次引用
- SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep ReasoningShuzheng Gao, Chaozheng Wang, Cuiyun Gao, Michael R. LyuICSE 2026 · 1 次引用
- VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security SpecificationsHao Zhu, Jia Li, Cuiyun Gao, Jiaru Qian 等FSE 2026
它引用的 Paper14
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning 等NeurIPS 2023 · 10,924 次引用
- CodeBERT: A Pre-Trained Model for Programming and Natural LanguagesZhangyin Feng, Daya Guo, Duyu Tang, Nan Duan 等EMNLP Findings 2020 · 2,828 次引用
- Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine TranslationHaoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan 等ICML 2024 · 447 次引用
- Enhancing Static Analysis for Practical Bug Detection: An LLM-Integrated ApproachHaonan Li, Yu Hao, Yizhuo Zhai, Zhiyun QianOOPSLA 2024 · 142 次引用
- Data Quality for Software Vulnerability DatasetsRoland Croft, Muhammad Ali Babar, M. Mehdi KholoosiICSE 2023 · 138 次引用
相关 Paper
- Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability DetectionXin Peng, Bo Lin, Jing Wang, Xiaoling Li 等FSE 2026 · 1 次引用
- RealVul: Can We Detect Vulnerabilities in Web Applications with LLM?Di Cao, Yong Liao, Xiuwei ShangEMNLP 2024 · 11 次引用
- Vulnerability Detection with Code Language Models: How Far are We?Yangruibo Ding, Yanjun Fu, Omniyyah Ibrahim, Chawin Sitawarin 等ICSE 2025 · 44 次引用
- Enhancing Vulnerability Detection via Inter-procedural Semantic CompletionBozhi Wu, Chengjie Liu, Zhiming Li, Yushi Cao 等ISSTA 2025 · 2 次引用
- Thought Is All You Need: Smart Contract Vulnerability Detection with Thought-Augmented Large Language ModelChaoyuan Peng, Muhui Jiang, Yajin Zhou, Lei WuFSE 2026
