1. Can LLM Prompting Serve as a Proxy for Static Analysis in Vulnerability Detection
- Author
-
Ceka, Ira, Qiao, Feitong, Dey, Anik, Valecha, Aastha, Kaiser, Gail, and Ray, Baishakhi
- Subjects
Computer Science - Cryptography and Security ,Computer Science - Artificial Intelligence ,Computer Science - Computation and Language ,Computer Science - Software Engineering - Abstract
Despite their remarkable success, large language models (LLMs) have shown limited ability on applied tasks such as vulnerability detection. We investigate various prompting strategies for vulnerability detection and, as part of this exploration, propose a prompting strategy that integrates natural language descriptions of vulnerabilities with a contrastive chain-of-thought reasoning approach, augmented using contrastive samples from a synthetic dataset. Our study highlights the potential of LLMs to detect vulnerabilities by integrating natural language descriptions, contrastive reasoning, and synthetic examples into a comprehensive prompting framework. Our results show that this approach can enhance LLM understanding of vulnerabilities. On a high-quality vulnerability detection dataset such as SVEN, our prompting strategies can improve accuracies, F1-scores, and pairwise accuracies by 23%, 11%, and 14%, respectively.
- Published
- 2024