Computer ScienceProceedings of the 33rd USENIX Security Symposium
PENTESTGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing
G. Deng, Y. Liu, et al.
LLMs promise to transform penetration testing—this study builds a real-world benchmark and shows they excel at sub-tasks but struggle with whole-context reasoning. Introducing PENTESTGPT, a three-module, LLM-driven framework that boosts task completion by 228.6% over GPT-3.5 and succeeds on real-world targets and CTFs. The research was conducted by the authors present in <Authors> tag and PENTESTGPT is open-sourced with strong community uptake.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Linguistics and Languages
Applying large language models for automated essay scoring for non-native Japanese
W. Li and H. Liu
Medicine and Health
Leveraging Large Language Models for Precision Monitoring of Chemotherapy-Induced Toxicities: A Pilot Study with Expert Comparisons and Future Directions
O. R. Sarrias, M. P. M. D. Prado, et al.
Computer Science
The Potential and Limitations of Large Language Models for Text Classification through Synthetic Data Generation
A. K. P. Venkata and L. Gudala
Computer Science
Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models
J. Chen, Y. Zhang, et al.
