
giskard-oss
🐢 Open-Source Evaluation & Testing library for LLM Agents
adversarial-attackai-securityfuzzing+3

🐢 Open-Source Evaluation & Testing library for LLM Agents

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

Metasploit for machine learning.