1. Home
  2. About the authors
  3. Frequently Asked Questions (FAQ)
  4. License
  5. How to read this book?
  7. Attacks
  9. 1. Prompt Engineering
    1. 1.1. Bijection Learning
  11. 2. Model Architecture Exploitation
  12. 3. ML Systems
    1. 3.1. Attacks on Quantization Techniques
      1. 3.1.1. Adversarial Interferences on GGUF
    3. 3.2. Attacks on KV Cache
      1. 3.2.1. Prompt Leakage via KV Cache Sharing
  14. 4. Application Protocols
    1. 4.1. Model Context Protocol
      1. 4.1.1. Ghost Tool Shadowing
  17. Defenses and Guardrails
  19. 5. Cloud Guardrails
    1. 5.1. AWS Bedrock
  21. 6. Hardware Protections
  23. Alignment, Safety, and Responsible AI
  25. 7. Model Steering
  26. 8. Evaluations
  28. Conclusion
  30. 9. Appendix
    1. 9.1. Additional Reading

AI Security Handbook: Develop Secure AI Systems