CurriculumPT: LLM-Based Multi-Agent Autonomous Penetration Testing with Curriculum-Guided Task Scheduling
Applied Sciences · 18.08.2025 · 15 (16) · 9096
DOI: 10.3390/app15169096 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 18.08.2025. Verfasst von Xingyu Wu und 8 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Central Funds Guiding the Local Science and Technology Development, Fundamental Research Funds for the Central Universities, the National Natural Science Foundation of China.
Abstract (Originalsprache)
While autonomous driving systems and intelligent transportation infrastructures become increasingly software-defined and network-connected, ensuring their cybersecurity has become a critical component of traffic safety. Large language models (LLMs) have recently shown promise in automating aspects of penetration testing, yet most existing approaches remain limited to simple, single-step exploits. They struggle to handle complex, multi-stage vulnerabilities that demand precise coordination, contextual reasoning, and knowledge reuse. This is particularly problematic in safety-critical domains, such as autonomous vehicles, where subtle software flaws can cascade across interdependent subsystems. In this work, we present CurriculumPT, a novel LLM-based penetration testing framework specifically designed for the security of intelligent systems. CurriculumPT combines curriculum learning and a multi-agent system to enable LLM agents to progressively acquire and apply exploitation skills across common vulnerabilities and exposures-based tasks. Through a structured progression from simple to complex vulnerabilities, agents build and refine an experience knowledge base that supports generalization to new attack surfaces without requiring model fine-tuning. We evaluate CurriculumPT on 15 real-world vulnerabilities scenarios and demonstrate that it outperforms three state-of-the-art baselines by up to 18 percentage points in exploit success rate, while achieving superior efficiency in execution time and resource usage. Our results confirm that CurriculumPT is capable of autonomous, scalable penetration testing and knowledge transfer, laying the groundwork for intelligent security auditing of modern autonomous driving systems and other cyberphysical transportation platforms.
Förderung
- the Central Funds Guiding the Local Science and Technology Development
- Fundamental Research Funds for the Central Universities
- the National Natural Science Foundation of China
Zitieren
APA
Wu, X., Tian, Y., Chen, Y., Ye, P., Cui, X., Jia, J., Li, S., Liu, J., & Niu, W. (2025). CurriculumPT: LLM-Based Multi-Agent Autonomous Penetration Testing with Curriculum-Guided Task Scheduling. Applied Sciences, 15(16), 9096. https://doi.org/10.3390/app15169096
Vancouver
Wu X, Tian Y, Chen Y, Ye P, Cui X, Jia J, et al. CurriculumPT: LLM-Based Multi-Agent Autonomous Penetration Testing with Curriculum-Guided Task Scheduling. Applied Sciences. 2025;15(16):9096. doi:10.3390/app15169096
BibTeX
@article{Wu2025,
author = {Wu, Xingyu and Tian, Yunzhe and Chen, Yuanwan and Ye, Ping and Cui, Xiaoshu and Jia, Jingqi and Li, Shouyang and Liu, Jiqiang and Niu, Wenjia},
title = {CurriculumPT: LLM-Based Multi-Agent Autonomous Penetration Testing with Curriculum-Guided Task Scheduling},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {16},
pages = {9096},
doi = {10.3390/app15169096}
}
EUVIMED