Step into the role of a Senior Security Engineer at PseudoCo and take on a mission to secure AI sprawl across the enterprise. Across four real-world use cases and fifteen success criteria. You will:
- Discover AI assets
- Validate models with algorithmic red teaming
- Scan model files for embedded threats
- Build runtime policies that block security threats, sensitive data, and harmful language in real time.
Then you'll go deeper into agentic AI by inspecting flows for agent-specific attacks such as tool poisoning, prompt injection, and rug pull attacks.