Gemini 1.5
Google DeepMind — Gemini
rich detail 10 method fields published
Evaluation
Divergence attack training-data extraction evaluation (Nasr et al.)
Divergence attack (Nasr et al. 2023) prompting the model to repeat a single token many times, testing divergence and training-data emission; also long-prompt variant (1,000 vs 999,000 repetitions)
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.