Hands-on notes and labs from my AI security learning path.
- HackTheBox Academy - AI Red Teamer path (Hard · 12 modules · ~18 days)
- TryHackMe - AI Security path (Medium · 5 modules · 26 labs)
- Fundamentals of AI (in progress)
- Applications of AI in InfoSec
- Introduction to Red Teaming AI
- Prompt Injection Attacks
- LLM Output Attacks
- AI Data Attacks
- Attacking AI - Application and System
- AI Evasion - Foundations
- AI Evasion - First-Order Attacks
- AI Evasion - Sparsity Attacks
- AI Privacy
- AI Defense
Section 1 - AI Fundamentals
- AI/ML Security Threats
- AI Models & Data
- Prompt Engineering
- AI Forensics
- ContAInment
Section 2 - Secure AI Systems
- Securing AI Systems
- LLM Security
- AI Threat Modelling
- AI System Reconnaissance
- AI Threat Modelling Assessment
Section 3 - Prompt Security
- Prompt Injection
- Jailbreaking
- Prompt Defence
- LLMborghini
- White Rabbit
Section 4 - AI Supply Chain Security
- Understanding AI Supply Chains
- Supply Chain Attack Vectors
- Securing the AI Supply Chain
- Payload
- Checkpoint
Section 5 - Data Poisoning
- RAG Security Fundamentals
- Data Poisoning in RAG Systems
- Sensitive Information Disclosure
- UnIndexed
- Lockdown
Each module has its own folder containing:
notes.md- key concepts, techniques, and observationslabs.md- lab walkthrough notes and findings (where applicable)
AI security is an emerging discipline with a critical gap between traditional security frameworks and the actual threat surface of AI systems. These notes document hands-on learning in offensive and defensive AI security techniques - directly supporting my work on the KAICSF framework.