ai-llm-red-team-handbook/docs/SUMMARY.md

Summary

• 1. Introduction to AI Red Teaming
• 2. Ethics, Legal, and Stakeholder Communication
• 3. The Red Teamer's Mindset
• 4. SOW, Rules of Engagement, and Onboarding
• 5. Threat Modeling and Risk Analysis
• 6. Scoping an Engagement
• 7. Lab Setup and Environmental Safety
• 8. Evidence Documentation and Chain of Custody
• 9. LLM Architectures and System Components
• 10. Tokenization, Context, and Generation
• 11. Plugins, Extensions, and External APIs
• 12. Retrieval Augmented Generation (RAG) Pipelines
• 13. Data Provenance and Supply Chain Security
• 14. Prompt Injection
• 15. Data Leakage and Extraction
• 16. Jailbreaks and Bypass Techniques
• 17. Plugin and API Exploitation
  • API Authentication and Authorization
  • Plugin Vulnerabilities
  • API Exploitation and Function Calling
  • Third Party Risks and Testing
  • Case Studies and Defense
• 18. Evasion, Obfuscation, and Adversarial Inputs
• 19. Training Data Poisoning
• 20. Model Theft and Membership Inference
• 21. Model DoS and Resource Exhaustion
• 22. Cross-Modal and Multimodal Attacks
• 23. Advanced Persistence and Chaining
• 24. Social Engineering LLMs
• 25. Advanced Adversarial ML
• 26. Supply Chain Attacks on AI
• 27. Federated Learning Attacks
• 28. AI Privacy Attacks
• 29. Model Inversion Attacks
• 30. Backdoor Attacks
• 31. AI System Reconnaissance
• 32. Automated Attack Frameworks
• 33. Red Team Automation
• 34. Defense Evasion Techniques
• 35. Post-Exploitation in AI Systems
• 36. Reporting and Communication
• 37. Remediation Strategies
• 38. Continuous Red Teaming
• 39. AI Bug Bounty Programs
• 40. Compliance and Standards
• 41. Industry Best Practices
• 42. Case Studies and War Stories
• 43. Future of AI Red Teaming
• 44. Emerging Threats
• 45. Building an AI Red Team Program
• 46. Conclusion and Next Steps