收藏切换
ValidPoC: LLM-Based Generation and Verification Method of PoC-Nuclei Templates for Vulnerability Reproduction
收藏切换
Yiming Wu1, Jiamei Chi2, Chenghao Chen2, Zhenyu Wen1, *, Zhen Hong1, Xinwei Yao3, Shouling Ji4
Journal of Computer Research and Development | 2026, 63(10) : 2611 - 2631
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(10): 2611-2631
• Special Issue on Security Protection Technology of Massive Heterogeneous Terminals in Dynamic Heterogeneous Networks •
ValidPoC: LLM-Based Generation and Verification Method of PoC-Nuclei Templates for Vulnerability Reproduction
Full
Yiming Wu1, Jiamei Chi2, Chenghao Chen2, Zhenyu Wen1, *, Zhen Hong1, Xinwei Yao3, Shouling Ji4
Affiliations
  • 1Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310014
  • 2College of Information Engineering, Zhejiang University of Technology, Hangzhou 310014
  • 3Academy for Advanced Interdisciplinary Science and Technology (Zhejiang University of Technology), Hangzhou 310014
  • 4College of Computer Science and Technology, Zhejiang University, Hangzhou 310027
  • born in 1996. PhD, assistant researcher, master supervisor. Member of CCF. Her main research interests include data-driven security, black industry mining, and cybercrime research

    born in 2002. Master candidate. Her main research interests include AI security, big data analytics, and data-driven security

    born in 2001. Master candidate. Her main research interests include LLM security, AI system, and system security

    born in 1987. PhD, professor, PhD supervisor. Member of CCF. His main research interests include IoT, crowd sources, AI system, and cloud computing

    born in 1983. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include Internet of things, information physical systems, intelligent systems security, big data analytics, and artificial intelligence

    born in 1986. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include collective intelligence computing, collective intelligence sensing and collaboration, and intelligent Internet of things

    born in 1986. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include data-driven security and privacy, AI security, and big data mining and analytics

About Author:

born in 1996. PhD, assistant researcher, master supervisor. Member of CCF. Her main research interests include data-driven security, black industry mining, and cybercrime research

born in 2002. Master candidate. Her main research interests include AI security, big data analytics, and data-driven security

born in 2001. Master candidate. Her main research interests include LLM security, AI system, and system security

born in 1987. PhD, professor, PhD supervisor. Member of CCF. His main research interests include IoT, crowd sources, AI system, and cloud computing

born in 1983. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include Internet of things, information physical systems, intelligent systems security, big data analytics, and artificial intelligence

born in 1986. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include collective intelligence computing, collective intelligence sensing and collaboration, and intelligent Internet of things

born in 1986. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include data-driven security and privacy, AI security, and big data mining and analytics

Published: 2026-10-01 doi: 10.7544/issn1000-1239.202660432
Outline
收藏切换

External vulnerability knowledge is increasingly important for large language models (LLMs) to understand vulnerability targets, craft exploit payloads, and interpret verification evidence. Recent approaches incorporate external vulnerability knowledge via prompt, task planning and multi-agent collaboration, to improve automated penetration testing. However, automated vulnerability reproduction remains challenging because public exploit materials are often heterogeneous and loosely structured, spanning scripts, HTTP requests, command-line snippets, and walkthrough in natural language. Prior work has leveraged retrieval-augmented generation, PoC semantic repair, and exploit code generation to better utilize external vulnerability knowledge, but still constrained by environment dependencies, exploit semantic extraction and model hallucinations, weakening the trustworthiness of automated reproduction.

To address these issues, we propose ValidPoC, an LLM-driven framework for automated vulnerability reproduction that can convert heterogeneous exploit walkthrough or scripts into structured and reliable PoC-Nuclei templates. Specifically, ValidPoC defines a PoC semantic model that provides a unified representation of exploit logic, including request construction, payload generation, execution dependencies, and verification criteria. We develop a Semgrep-assisted semantic parsing mechanism to extract PoC Semantic IR from public exploit materials, including exploit scripts and natural-language descriptions, and construct structured Nuclei YAML templates for automated vulnerability reproduction. To improve reproduction reliability, we establish a closed-loop execution–evaluation–repair framework and a three-level validation model (L1–L3) for cross-validation across multiple execution evidence.We evaluate ValidPoC on 67 real-world vulnerability reproduction tasks. ValidPoC achieves a Pass@3 reproduction rate of 76.12% and consistently surpasses existing automated penetration testing frameworks, including PentestAgent and PentestGPT. In addition, it maintains competitive efficiency with respect to both execution time and token usage. These results demonstrate the effectiveness of ValidPoC in understanding heterogeneous exploit materials, generating PoC templates, and vulnerability reproduction.

automated vulnerability reproduction  /  large language models  /  PoC semantic parsing  /  Nuclei template generation  /  multi-agent collaboration
伍一鸣, 池家梅, 陈城浩, 温震宇, 洪榛, 姚信威, 纪守领. ValidPoC:基于大语言模型的PoC-Nuclei模板生成与漏洞复现验证方法. 计算机研究与发展, 2026 , 63 (10) : 2611 -2631 . DOI: 10.7544/issn1000-1239.202660432
Yiming Wu, Jiamei Chi, Chenghao Chen, Zhenyu Wen, Zhen Hong, Xinwei Yao, Shouling Ji. ValidPoC: LLM-Based Generation and Verification Method of PoC-Nuclei Templates for Vulnerability Reproduction[J]. Journal of Computer Research and Development, 2026 , 63 (10) : 2611 -2631 . DOI: 10.7544/issn1000-1239.202660432
Year 2026 volume 63 Issue 10
61
29
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202660432
  • Receive Date:2026-06-06
  • Online Date:2026-11-17
  • Published:2026-10-01
Article Data
Affiliations
History
  • Received:2026-06-06
  • Revised:2026-07-10
Affiliations
    1Institute of Cyberspace Security, Zhejiang University of Technology, Hangzhou 310014
    2College of Information Engineering, Zhejiang University of Technology, Hangzhou 310014
    3Academy for Advanced Interdisciplinary Science and Technology (Zhejiang University of Technology), Hangzhou 310014
    4College of Computer Science and Technology, Zhejiang University, Hangzhou 310027
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202660432
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT