Gemini

The 'Gemini' dataset is a benchmark used to evaluate the effectiveness of injection detection in multi-agent LLM systems, specifically focusing on the detection of domain camouflaged injection attacks.

Papers using Gemini (2)

Ask the Right Comparison:Bias-Aware Bayesian Active Top-$k$ Ranking with LLM Judges2026Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems2026