AI Security and Safety¶
Use this track for the control layer around AI systems: guardrails, prompt injection, red-teaming, policy enforcement, privacy boundaries, ethics, risk, and fairness.
This track complements ../01_ai_engineering/. Build the agent shape there, then use this track to constrain what the system is allowed to see, decide, call, and return.
| Module | Focus | Folder |
|---|---|---|
| 00 | Safety guardrail design | 00_safety_guardrail_design/ |
| 01 | Prompt-injection security | 01_prompt_injection_security/ |
| 02 | AI ethics, risk, and fairness | 02_ai_ethics_risk_fairness/ |
| 03 | Data access governance | 03_data_access_governance/ (placeholder) |