
ActGuard
Pre-execution action-auditing defense that detects and masks indirect prompt injection in tool-using LLM agents using embedding retrieval and…
ai-securitydefensive-toolsmachine-learning+2

Pre-execution action-auditing defense that detects and masks indirect prompt injection in tool-using LLM agents using embedding retrieval and…

Privacy testing library for deep learning systems, enabling assessment of susceptibility to membership inference, model extraction, and model…