Can Open Large Language Models Catch Vulnerabilities?
Lists
Only you see this
Abstract
As Large Language Models (LLMs) become increasingly integrated into secure software development workflows, a critical question remains unanswered: can these models not only detect insecure code but also reliably classify vulnerabilities according to standardized taxonomies? In this work, we conduct a systematic evaluation of three state-of-the-art LLMs - Llama3, Codestral, and Deepseek R1 - using a carefully filtered subset of the Big-Vul dataset annotated with eight representative Common Weakness Enumeration categories. Adopting a closed-world classification setup, we assess each model’s performance in both identifying the presence of vulnerabilities and mapping them to the correct CWE label. Our findings reveal a sharp contrast between high detection rates and markedly poor classification accuracy, with frequent overgeneralization and misclassification. Moreover, we analyze model-specific biases and common failure modes, shedding light on the limitations of current LLMs in performing fine-grained security reasoning.These insights are especially relevant in educational contexts, where LLMs are being adopted as learning aids despite their limitations. A nuanced understanding of their behaviour is essential to prevent the propagation of misconceptions among students. Our results expose key challenges that must be addressed before LLMs can be reliably deployed in security-sensitive environments.
BibTeX
@misc{deepseekai2025can,
author = {DeepSeek-AI and Daya Guo and Dejian Yang and Haowei Zhang and Junxiao Song and Ruoyu Zhang and Runxin Xu and Qihao Zhu and Shirong Ma and Peiyi Wang and Xiao Bi and Xiaokang Zhang and Xingkai Yu and Yu Wu and Zhenhua Wu and Zhibin Gou and Zhihong Shao and Zhuoshu Li and Ziyi Gao and Aixin Liu and Bing Xue and Bingxuan Wang and Bowen Wu and Bei Feng and Chengda Lu and Chenggang Zhao and Chengqi Deng and Chenyu Zhang and Chong Ruan and Damai Dai and Deli Chen and Dongjie Ji and Erhang Li and Fangyun Lin and Fengze Dai and Fuli Luo and Guangbo Hao and Guan-Ting Chen and Guowei Li and Hongjun Zhang and Han Bao and Hanwei Xu and Haocheng Wang and Honghui Ding and Huajian Xin and Huazuo Gao and Hui Qu and Hui Li and Jianzhong Guo and Jiashi Li and Jiawei Wang and Jingchang Chen and Jingyang Yuan and Junjie Qiu and Junlong Li and Jiali Cai and Jiaqi Ni and Jian Liang and Jing Chen and Kai Dong and Kai Hu and Kaige Gao and Kang Guan and Kexin Huang and Kuai Yu and Lean Wang and Lecong Zhang and Liang Zhao and Litong Wang and Liyue Zhang and Lei Xu and L. Xia and Mingchuan Zhang and Minghua Zhang and Minghui Tang and Meng Li and Miaojun Wang and Mingming Li and Ning Tian and Panpan Huang and Peng Zhang and Qiancheng Wang and Qinyu Chen and Qiushi Du and Ruiqi Ge and Ruisong Zhang and Rui‐Le Pan and Runji Wang and R. J. Chen and Rong Jin and Ruyi Chen and Shanghao Lu and Shangyan Zhou and Shanhuang Chen and Shengfeng Ye and Shiyu Wang and Shuiping Yu and Shunfeng Zhou and Shuting Pan and Sansan Li},
title = {{Can Open Large Language Models Catch Vulnerabilities?}},
year = {2025},
eprint = {2501.12948},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2501.12948},
howpublished = {arXiv},
}