BigVul

BigVul is a benchmark dataset used to evaluate the effectiveness of deep learning models in detecting software vulnerabilities.

Papers using BigVul (14)

SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?2023 · 10 citesK-ASTRO: Structure-Aware Adaptation of LLMs for Code Vulnerability Detection2022 · 3 citesAn Empirical Evaluation of LLM-Based Approaches for Code Vulnerability Detection: RAG, SFT, and Dual-Agent Systems2026LLMs in Code Vulnerability Analysis: A Proof of Concept2026Llama-based source code vulnerability detection: Prompt engineering vs Fine tuning2025From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection2025Ensembling Large Language Models for Code Vulnerability Detection: An Empirical Evaluation2025Data and Context Matter: Towards Generalizing AI-based Software Vulnerability Detection2025Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization2025Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?2025Vulnerability Detection with Code Language Models: How Far Are We?2024 · 13 citesMultitask-based Evaluation of Open-Source LLM on Software Vulnerability2024 · 1 citesPros and Cons! Evaluating ChatGPT on Software Vulnerability2024Security Vulnerability Detection with Multitask Self-Instructed Fine-Tuning of Large Language Models2024