iSEngLab/LLM4VulFix

[2023 TDSC] Pre-trained Model-based Automated Software Vulnerability Repair: How Far are We?

22
/ 100
Experimental

This project helps software security researchers evaluate and benchmark different pre-trained models designed to automatically fix software vulnerabilities. It takes as input various software vulnerability datasets and pre-trained models, and outputs performance metrics showing how effectively these models can repair code. Security researchers and academics working on automated program repair would use this to understand the current state-of-the-art.

No commits in the last 6 months.

Use this if you are a security researcher or academic interested in replicating or extending research on automated software vulnerability repair using pre-trained models.

Not ideal if you are a software developer looking for a plug-and-play tool to automatically fix vulnerabilities in your production code.

software-security-research vulnerability-repair automated-code-fixing academic-benchmarking program-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

25

Forks

2

Language

Python

License

Last pushed

Jun 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/iSEngLab/LLM4VulFix"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.