VIIIProgram
AI Security
Attacking and defending AI systems.
- 801Course
Prompt Injection
The attack every AI system faces.
4 lessons·PractitionerThe attack - 802Course
Data Poisoning
The training-time attack.
3 lessons·PractitionerThe attack - 803Course
Model Theft and Extraction
Stealing a model through its API.
3 lessons·PractitionerThe attack - 804Course
Jailbreaks
Bypassing the guardrails.
3 lessons·PractitionerThe category - 805Course
Security Testing for AI
The QA discipline for AI security.
3 lessons·PractitionerThe practice - 806Course
AI Red Teaming
The offensive discipline.
3 lessons·PractitionerThe engagement - 807Course
Secure Deployment
Defensive engineering.
3 lessons·PractitionerThe practice - 808Course
Adversarial Examples
The classical ML attack, updated.
3 lessons·PractitionerThe attack - 809Course
Model Privacy
Protecting training data and users.
3 lessons·PractitionerThe techniques