LLMs overestimate CVSS severity on bug bounty reports
Best prompting reached 49.58% level accuracy on 240 vendor-validated Huntr reports; fine-tuning a 7B model hit 56.25%.
Stories per day · 30 days
2 RSS
2 stories, newest first · one card per story
Stories tagged #severity-scoring
Most high-severity cloud security findings are downgraded once an AI agent checks the environment
Sola Security's AI agent changed grades on 75.1% of 9,967 high-severity cloud findings, mostly downward.
7