AI Safety & Security
Defend AI systems: injection, jailbreaks, red-teaming, data handling, and governance.
This track assumes you already know
- 1
Attack surface
- Prompt Injection Instructions and data arrive as the same thing. That is the vulnerability, it has no complete fix, and the defense is architectural. Security
- Jailbreaks and Guardrails Why safety training is a tendency rather than a rule, and how to build the enforcement layer that does hold. Security
- Red-Teaming AI Systems Adversarial testing of your own system before someone else does it. What to try, how to organize it, and what to do with findings. Security
- 2
Content and data
- Content Moderation Filtering what goes in and what comes out. Where classifiers belong, and why over-blocking is as real a failure as under-blocking. Security
- Handling PII and Sensitive Data Prompts leave your infrastructure, logs persist, and models memorize. Three exposure paths and what to do about each. Security
- Model Supply Chain Risk Downloading weights runs someone else's file on your hardware. What can hide in a model, an adapter, or a tool server. Security
- 3
Governance and evaluation
- AI Governance and Compliance The documentation and process obligations around shipping AI. What holds regardless of jurisdiction, and what to write down. Security
- Human Evaluation and Annotation Agreement For subjective quality, humans are the ground truth. But humans disagree, so you have to measure whether your labels are consistent enough to trust. Evaluation