LLMSecEval

LLMSecEval is a benchmark dataset used to evaluate the security of code generated by Large Language Models (LLMs) by assessing their ability to identify and address vulnerabilities.

Papers using LLMSecEval (3)

Cross-Cutting Security Analysis of LLM-Generated Code via Metamorphic Testing and Association Rule Mining2026SOSecure: Safer Code Generation with RAG and StackOverflow Discussions2025LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluations2023 · 41 cites