Workshop: Hacking AI-LLM Applications with Brian Fehrman, Joff Thyer and Derek Banks

Workshop Syllabus: Hacking AI-LLM Applications

1. AI & Machine Learning Essentials

• AI, ML, and Deep Learning overview
• Supervised vs. Unsupervised learning
• Neural networks and model training
• Generative vs. Discriminative models
• Practical applications in cybersecurity

2. Large Language Models (LLMs)

• What LLMs are and how they work
• Transformer architecture (encoder, decoder types)
• Key capabilities: NLP, text generation, reasoning
• Context windows and system prompts

3. Prompt Engineering

• Elements of effective prompts
• Prompting techniques:
  • Zero-shot, few-shot, chain-of-thought
  • Generated knowledge and emotional prompting
• Iterative refinement strategies

4. Secure AI System Design

• Open WebUI architecture and components
• Retrieval-Augmented Generation (RAG) flow
• Vector databases and embedding security risks
• Tools and pipelines in Open WebUI
• Deploying filters (e.g. prompt injection, PII, toxicity)

5. AI Security Threats

• AI safety vs. security concerns
• OWASP LLM Top 10 risks
• Common attack vectors:
  • Prompt injection, system prompt leaks, jailbreaking
  • Role deception, confusion tactics, custom encoding
  • External malicious content, escalation chains

6. Offensive AI Use Cases (with demonstrations)

• Adversarial LLM prompt design
• Bypassing safeguards
• Leveraging agentic and interpreter capabilities
• Attacking RAG
• Tooling to assist with attacks and assessments