CASEY is an innovative approach that leverages Large Language Models to automate and improve security vulnerability triage, reducing manual effort while maintaining accuracy.

• Automatically identifies Common Weakness Enumerations (CWEs) for security bugs
• Assesses vulnerability severity to prioritize critical issues
• Processes high volumes of bug reports efficiently
• Maintains human-comparable accuracy while reducing resource requirements

This research has significant implications for security teams facing growing vulnerability backlogs, enabling more efficient allocation of resources to the most critical security threats while reducing triage time and costs.

Streamlining Security Vulnerability Triage with Large Language Models