UCSB-SURFI/VulnLLM-R-7B

UCSB-SURFI/VulnLLM-R-7B is the first specialized 7 billion parameter reasoning Large Language Model developed by UCSB-SURFI for software vulnerability detection. Unlike traditional tools, it generates a "Chain-of-Thought" to analyze why a vulnerability exists, mimicking human security auditing. This model excels at identifying complex logic vulnerabilities across C, C++, Python, and Java, outperforming larger general-purpose models and industry-standard tools.