Skip to content

Table of Contents

MLSecOps Practical Reference Guide v1.1.0 — Securing AI Systems Across the Lifecycle


Chapter 1: Abstract and Introduction

Chapter 2: Scope, Audience, and Threat Model

Chapter 3: Autonomous AI Threats and Offensive AI Operations

Chapter 4: Data Security and Privacy

Chapter 5: Model, Artifact, and Supply Chain Security

Chapter 6: MLSecOps Lifecycle Control Model

Chapter 7: LLM and RAG Security

Chapter 9: Anti-patterns in MLSecOps

Chapter 10: Monitoring, SOC, and Incident Response

Chapter 11: Governance, Compliance, and Evidence Pack

Chapter 12: Threat, Control, and Tool Mapping

Chapter 13: Case Studies and Lessons Learned

Chapter 14: MLSecOps Maturity Roadmap

Chapter 15: Conclusion and Appendices

Chapter 16: Kubernetes Deployment Reference

Appendix E: Implementation Reference


Reading Paths

Goal Start here
Executive overview Ch. 1 → Ch. 2 → Ch. 14
Threat understanding Ch. 3 (demonstrated first) → Ch. 2 (attack surface) → Ch. 13
Implementation Ch. 6 → Ch. 12 (mapping; CLI appendix optional) → Ch. 15 (checklists)
LLM / RAG / Agent Ch. 7 → Ch. 8 → Ch. 9
Managed AI API only Ch. 2 (managed AI) → Ch. 7 → Appendix D
Shadow AI / governance Ch. 2 → Ch. 11 → Ch. 13 (Samsung) → Ch. 9 (anti-patterns)
MCP security Ch. 7 → Ch. 8 (MCP tools) → Ch. 12 (scan tools) → Ch. 13 (lab)
Operations & SOC Ch. 10 → Ch. 11
Implementation in production Appendix E → Ch. 6 → Ch. 12
Kubernetes deployment Ch. 16 (architecture patterns; test IaC in your cluster)