Codexity: Secure AI-assisted Code Generation
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_ | 1866913343233589248 |
|---|---|
| author | Kim, Sung Yong Fan, Zhiyu Noller, Yannic Roychoudhury, Abhik |
| author_facet | Kim, Sung Yong Fan, Zhiyu Noller, Yannic Roychoudhury, Abhik |
| contents | Despite the impressive performance of Large Language Models (LLMs) in software development activities, recent studies show the concern of introducing vulnerabilities into software codebase by AI programming assistants (e.g., Copilot, CodeWhisperer). In this work, we present Codexity, a security-focused code generation framework integrated with five LLMs. Codexity leverages the feedback of static analysis tools such as Infer and CppCheck to mitigate security vulnerabilities in LLM-generated programs. Our evaluation in a real-world benchmark with 751 automatically generated vulnerable subjects demonstrates Codexity can prevent 60% of the vulnerabilities being exposed to the software developer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_03927 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Codexity: Secure AI-assisted Code Generation Kim, Sung Yong Fan, Zhiyu Noller, Yannic Roychoudhury, Abhik Software Engineering Despite the impressive performance of Large Language Models (LLMs) in software development activities, recent studies show the concern of introducing vulnerabilities into software codebase by AI programming assistants (e.g., Copilot, CodeWhisperer). In this work, we present Codexity, a security-focused code generation framework integrated with five LLMs. Codexity leverages the feedback of static analysis tools such as Infer and CppCheck to mitigate security vulnerabilities in LLM-generated programs. Our evaluation in a real-world benchmark with 751 automatically generated vulnerable subjects demonstrates Codexity can prevent 60% of the vulnerabilities being exposed to the software developer. |
| title | Codexity: Secure AI-assisted Code Generation |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2405.03927 |