LLMVul: A Vulnerability-Labeled Dataset of LLM-Generated C/C++ Functions from Real Production Repositories
Source
Mohammad Farhad, Shuvalaxmi Dass
Author
Mohammad Farhad, Shuvalaxmi Dass
Date
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
Gives security researchers and tool builders a real-world, provenance-tracked dataset for studying how often and in what ways AI-generated code introduces vulnerabilities in production repositories, not just in synthetic benchmarks.
articleAutomated Vulnerability Injection in Smart Contracts Using Large Language ModelsLuca Migliaccio, Roberto Natella, Naghmeh Ivaki, Nuno Laranjeiro, Marco Vieira
articleHow effective are traditional test criteria at detecting bugs in large language models generated code?Asma Hamidi, Michael Konstantinou, Renzo Degiovanni, Mike Papadakis
articleDeepsecBenchMalte Ubl