Stage 4 · Mastery & Industry
Safety, Security & Governance
Prompt injection, misuse, alignment risks and the rules being written for AI.
3 lessons1 ready
- 01 Prompt Injection and Tool Poisoning Why agents that read untrusted content can be hijacked, and the defences that work. Intermediate 20 min ✓
- 02 AI Governance and Regulation EU AI Act, China's generative-AI measures, NIST AI RMF and what they require. Intermediate 20 min ✎ In progress
- 03 Alignment and Frontier Risks Specification gaming, deception evaluations and frontier safety frameworks. Expert 20 min ✎ In progress
Matching units in the new course
Each unit has goals, algorithms, must-read papers, a project and a self-test.
U92 Security: Jailbreaks, Injection & Privacy Adversarial examples, GCG, prompt injection, red-teaming, watermarking, differential privacy and backdoors. 6 h8 algorithms4 paperslesson ready U93 Frontier Risk, Scalable Oversight & Governance Weak-to-strong generalisation, debate, Constitutional AI, risk frameworks and regulation (EU AI Act, NIST AI RMF). 6 h4 algorithms3 papers