Prompt-Enhanced Software Vulnerability Detection Using ChatGPT
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911836745498624 |
|---|---|
| author | Zhang, Chenyuan Liu, Hao Zeng, Jiutian Yang, Kejing Li, Yuhong Li, Hui |
| author_facet | Zhang, Chenyuan Liu, Hao Zeng, Jiutian Yang, Kejing Li, Yuhong Li, Hui |
| contents | With the increase in software vulnerabilities that cause significant economic and social losses, automatic vulnerability detection has become essential in software development and maintenance. Recently, large language models (LLMs) like GPT have received considerable attention due to their stunning intelligence, and some studies consider using ChatGPT for vulnerability detection. However, they do not fully consider the characteristics of LLMs, since their designed questions to ChatGPT are simple without a specific prompt design tailored for vulnerability detection. This paper launches a study on the performance of software vulnerability detection using ChatGPT with different prompt designs. Firstly, we complement previous work by applying various improvements to the basic prompt. Moreover, we incorporate structural and sequential auxiliary information to improve the prompt design. Besides, we leverage ChatGPT's ability of memorizing multi-round dialogue to design suitable prompts for vulnerability detection. We conduct extensive experiments on two vulnerability datasets to demonstrate the effectiveness of prompt-enhanced vulnerability detection using ChatGPT. We also analyze the merit and demerit of using ChatGPT for vulnerability detection. Repository: https://github.com/KDEGroup/LLMVulnerabilityDetection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_12697 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Prompt-Enhanced Software Vulnerability Detection Using ChatGPT Zhang, Chenyuan Liu, Hao Zeng, Jiutian Yang, Kejing Li, Yuhong Li, Hui Software Engineering With the increase in software vulnerabilities that cause significant economic and social losses, automatic vulnerability detection has become essential in software development and maintenance. Recently, large language models (LLMs) like GPT have received considerable attention due to their stunning intelligence, and some studies consider using ChatGPT for vulnerability detection. However, they do not fully consider the characteristics of LLMs, since their designed questions to ChatGPT are simple without a specific prompt design tailored for vulnerability detection. This paper launches a study on the performance of software vulnerability detection using ChatGPT with different prompt designs. Firstly, we complement previous work by applying various improvements to the basic prompt. Moreover, we incorporate structural and sequential auxiliary information to improve the prompt design. Besides, we leverage ChatGPT's ability of memorizing multi-round dialogue to design suitable prompts for vulnerability detection. We conduct extensive experiments on two vulnerability datasets to demonstrate the effectiveness of prompt-enhanced vulnerability detection using ChatGPT. We also analyze the merit and demerit of using ChatGPT for vulnerability detection. Repository: https://github.com/KDEGroup/LLMVulnerabilityDetection. |
| title | Prompt-Enhanced Software Vulnerability Detection Using ChatGPT |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2308.12697 |