MatteoGuglielmi-tech/VuLLM: Thesis Submission - v1.0.0
Abstract
VuLLM v1.0.0 - Thesis Submission This release accompanies the master's thesis: "Fine-tuning Large Language Models for C Vulnerability Detection with Structured Reasoning" Contents Rust preprocessing pipeline (/rusty) Python training and evaluation scripts (/src/core/cot_training) Prompt configurations for ablation studies Diagnostic suite (24 handcrafted test cases) Requirements See pixi.toml for dependencies Rust 1.89+ for preprocessing pipeline Python 3.12 for ML experiments
Fields of Study & Subjects
Software Engineering Research
Software Testing and Debugging Techniques
Web Application Security Vulnerabilities
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 4 March 2026
- Language
- EN