Release
Google DeepMind details the security protections put in place for its Gemini 4 Argon model.
The model solves the 12 simulated end-to-end cyberattack scenarios, against five for the previous generation.
Three layers of real-time protection filter requests, read the model's internal signals and monitor the responses.
Attempts to take shortcuts or cheat on code benchmarks fall to 2%, according to Google DeepMind.
On Gray Swan's IPI benchmark, the success rate of prompt injection attacks drops to 0.7%.