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
1 stories, newest first · one card per story
1 stories, newest first · one card per story
Best prompting reached 49.58% level accuracy on 240 vendor-validated Huntr reports; fine-tuning a 7B model hit 56.25%.
Today 656 readers · 803 views · 606 reads · all time 158K views