Code Vulnerability Repair with Large Language Model using Context-Aware Prompt Tuning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915356961931264 |
|---|---|
| author | Khan, Arshiya Liu, Guannan Gao, Xing |
| author_facet | Khan, Arshiya Liu, Guannan Gao, Xing |
| contents | Large Language Models (LLMs) have shown significant challenges in detecting and repairing vulnerable code, particularly when dealing with vulnerabilities involving multiple aspects, such as variables, code flows, and code structures. In this study, we utilize GitHub Copilot as the LLM and focus on buffer overflow vulnerabilities. Our experiments reveal a notable gap in Copilot's abilities when dealing with buffer overflow vulnerabilities, with a 76% vulnerability detection rate but only a 15% vulnerability repair rate. To address this issue, we propose context-aware prompt tuning techniques designed to enhance LLM performance in repairing buffer overflow. By injecting a sequence of domain knowledge about the vulnerability, including various security and code contexts, we demonstrate that Copilot's successful repair rate increases to 63%, representing more than four times the improvement compared to repairs without domain knowledge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18395 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Code Vulnerability Repair with Large Language Model using Context-Aware Prompt Tuning Khan, Arshiya Liu, Guannan Gao, Xing Cryptography and Security Artificial Intelligence Large Language Models (LLMs) have shown significant challenges in detecting and repairing vulnerable code, particularly when dealing with vulnerabilities involving multiple aspects, such as variables, code flows, and code structures. In this study, we utilize GitHub Copilot as the LLM and focus on buffer overflow vulnerabilities. Our experiments reveal a notable gap in Copilot's abilities when dealing with buffer overflow vulnerabilities, with a 76% vulnerability detection rate but only a 15% vulnerability repair rate. To address this issue, we propose context-aware prompt tuning techniques designed to enhance LLM performance in repairing buffer overflow. By injecting a sequence of domain knowledge about the vulnerability, including various security and code contexts, we demonstrate that Copilot's successful repair rate increases to 63%, representing more than four times the improvement compared to repairs without domain knowledge. |
| title | Code Vulnerability Repair with Large Language Model using Context-Aware Prompt Tuning |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2409.18395 |