LlamaFirewall: Open-source framework to detect and mitigate AI centric security risks
It is designed to mitigate a wide spectrum of AI agent security risks including jailbreaking and indirect prompt injection, goal hijacking, and ...
Read the original at Help Net Security ↗
- Topics
- CybersecurityGovernance & Risk ManagementOpen-Source AIAI Agents & Automation
- Tracked via
- “AI Risks”