Artificial Intelligence
How to red-team a local LLM with garak 0.17 and Ollama
garak 0.17 is NVIDIA's LLM vulnerability scanner: it fires prompt injection, jailbreak, encoding and data-leak probes at your model and counts the failures. Against gemma3 1B on Ollama, on CPU, prompt injection succeeded 66.67% to 93.33% of the time, and a defensive system prompt did not stop it.