Phish or Legit: Do LLMs Know When NOT to Cry Wolf?

Automated excerpt

Most security benchmarks ask: "Can the model detect the threat? " That's the easy part. It's a 40-item cybersecurity triage benchmark with 20 threats and 20 legitimate messages. Three models achieved a perfect 1. 0 Balanced Accuracy.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.