I want to know how it works, how to attack it, and how to defend.
-
AI Security Fundamentals
How does the attack surface change when we add AI to a system?
-
Attack Techniques
How do attackers break AI systems?
-
Defensive Techniques
How do we stop these attacks?
-
Data Security
How do data and models leak information?
-
MLSecOps
At which stages of the model lifecycle should security controls be applied?
-
Tools
What can I test and use today?
-
RAG & Embeddings
How do we secure RAG and embeddings?
-
Secure AI Patterns
How should we design AI securely?
-
Testing
How do we know it’s secure?
-
Monitoring
How do we detect abuse in production?
-
Standards
How does this map to our security standards?
