AI Red Team - Book Structure

This document describes the logical structure of AI Red Team, Book 4 of The Transformed Architecture. The book is organised into eight parts with 28 numbered chapters, followed by the glossary, two appendices, the references and a note about the author. Parts II to VII follow the six Functions of NIST CSF 2.0, with Recover in a part of its own; Part VIII verifies the Functions with security chaos engineering, closes the purple loop and draws the conclusions. Every Category is treated through the three focus areas of the NIST Cyber AI Profile (CSF_COVERAGE.md). The book builds on the conclusions of Architecture as Code, AI Governance and AI Platform and Security, recorded in SERIES_FOUNDATIONS.md.

Chapter structure

Part I: Foundations

Chapter	File	Title	CSF 2.0	Description
1	01_introduction.md	Introduction: Putting AI to Work in Cyber Defence	–	Introduce the book on its own terms
2	02_threat_landscape.md	The Threat Landscape When Attackers Use AI	ID.RA	Give the defender's picture of what AI changes for attackers, based on observed evidence rather than forecasts, and translate it into requirements for each CSF Function. This is the threat picture behind the 'thwart' focus area throughout the book
3	03_csf_with_ai_focus.md	NIST CSF 2.0 with an AI Focus: Functions, Focus Areas and European Obligations	GV.OC	Present NIST CSF 2.0 as the organising frame of the book
4	04_reference_architecture.md	A Reference Architecture for AI-Enabled Cyber Defence	PR.PS, PR.IR	Present a reference architecture for AI-enabled cyber defence that places security AI on the governed platform of the earlier volumes, so that every later chapter has a common picture of where data, models, agents, tools, policy points, evidence and the separated ranges sit

Part II: Govern

Chapter	File	Title	CSF 2.0	Description
5	05_context_and_risk_strategy.md	Organisational Context and Risk Strategy for AI in Cyber Defence	GV.OC, GV.RM	Establish the organisational context and risk strategy for AI in cyber defence
6	06_roles_and_autonomy.md	Roles, Authorities and Autonomy Levels: People in Command of Security AI	GV.RR	Define roles, responsibilities and authorities when AI works in red, blue and purple teams, and the five autonomy levels that run through the book, so that people remain in command by design
7	07_policy_and_rules_of_engagement.md	Policy, Mandate and Rules of Engagement	GV.PO	Set out policy and mandate for AI in cyber defence
8	08_oversight_and_supply_chain.md	Oversight and AI Supply Chain Risk	GV.OV, GV.SC	Show how the management body oversees AI in cyber defence and how supply-chain risk is managed for AI

Part III: Identify

Chapter	File	Title	CSF 2.0	Description
9	09_asset_management.md	Asset Management for an Estate That Includes AI	ID.AM	Make asset management cover AI
10	10_threat_modelling_and_risk_assessment.md	AI-Assisted Threat Modelling and Risk Assessment	ID.RA	Show how AI makes threat modelling continuous and risk assessment evidence-based
11	11_vulnerability_and_exposure.md	Vulnerability Discovery and Exposure Management at Machine Speed	ID.RA, PR.PS	Show how defenders use AI to find and fix vulnerabilities in their own code and dependencies, prioritise exposure with EPSS, KEV and EUVD, delegate patch decisions in advance and absorb the patch wave without overwhelming reviewers
12	12_adversary_emulation.md	Adversary Emulation and Continuous Red Teaming with AI	ID.IM	Describe how a red team uses AI to emulate adversaries and validate controls continuously
13	13_red_teaming_ai_systems.md	Red Teaming AI Systems and Agents	ID.RA, ID.IM	Red team the organisation's own AI systems and agents

Part IV: Protect

Chapter	File	Title	CSF 2.0	Description
14	14_identity_and_access.md	Identity, Authentication and Access for People, Agents and Machines	PR.AA	Protect identities and access for people, service accounts and agents when attackers use AI
15	15_awareness_and_training.md	Awareness and Training: Resilience to AI-Generated Deception	PR.AT	Treat awareness and training as building resilience against AI-generated deception and as AI literacy for security staff
16	16_data_and_platform_security.md	Data and Platform Security with and for AI	PR.DS, PR.PS	Protect data and platforms with and for AI
17	17_infrastructure_resilience.md	Technology Infrastructure Resilience Against Machine-Speed Attacks	PR.IR	Make technology infrastructure resilient against machine-speed attacks

Part V: Detect

Chapter	File	Title	CSF 2.0	Description
18	18_ai_assisted_soc.md	The AI-Assisted Security Operations Centre	DE.CM, DE.AE	Describe the AI-assisted security operations centre
19	19_detection_intelligence_deception.md	Detection Engineering, Threat Intelligence and Deception as Code	DE.CM, DE.AE	Show how AI accelerates detection engineering as code, threat intelligence and deception

Part VI: Respond

Chapter	File	Title	CSF 2.0	Description
20	20_incident_management.md	Incident Management and Analysis with AI	RS.MA, RS.AN	Apply AI to incident management and analysis
21	21_reporting_and_mitigation.md	Incident Reporting, Communication and Mitigation	RS.CO, RS.MI	Cover incident reporting, communication and mitigation

Part VII: Recover

Chapter	File	Title	CSF 2.0	Description
22	22_recovery_plan_execution.md	Recovery Plan Execution with AI: From Incident to Restored Operations	RC.RP	Make recovery plan execution fast, verified and repeatable with AI
23	23_recovering_ai_systems.md	Recovering AI Systems and Security AI	RC.RP	Recover AI systems, and the security AI the organisation depends on, to a trustworthy state
24	24_proactive_recovery.md	Proactive Recovery: Recoverability, Rehearsal and Communication	RC.RP, RC.CO	Turn recovery from a reactive, rarely tested capability into a proactive, continuously verified one

Part VIII: Verification, Improvement and Conclusions

Chapter	File	Title	CSF 2.0	Description
25	25_security_chaos_engineering.md	Security Chaos Engineering with AI: Verifying Security Capabilities Continuously	ID.IM	Introduce security chaos engineering as the way to verify, continuously and in real time, that security capabilities across all six CSF Functions work as intended
26	26_purple_teaming_and_improvement.md	Purple Teaming, Measurement and Continuous Improvement	ID.IM, GV.OV	Close the loop across all Functions
27	27_conclusions_for_nordvik_and_hansa.md	Nordvik Region and Hansa Mutual: Cyber Defence Conclusions	–	Draw the conclusions for Nordvik Region and Hansa Mutual
28	28_conclusion.md	Conclusions: AI as an Active Part of Cyber Defence	–	Give the consolidated analysis

Appendices and Reference

Item	File	Title	Description
Glossary	29_glossary.md	Glossary	Defines the CSF, red-team, blue-team, AI-security and European regulatory vocabulary used in the book.
Appendix A	30_appendix_a_code_examples.md	Appendix A: Code Examples: Detection, Evaluation and Guardrail Artefacts	Complete versions of the artefacts in the chapters: CSF profiles as code, rules-of-engagement manifests, autonomy-level records, permission manifests and containment profiles for security AI, detection rules with tests, evaluation-harness configurations, finding records and metric definitions. No attack tooling.
Appendix B	appendix_templates_and_tools.md	Appendix B: Templates and Tools	Templates for CSF profiles, rules of engagement, exercise plans, finding records, autonomy-level decisions, purple-session agendas and supplier assurance questions.
References	31_references.md	References and Sources	Canonical bibliography
About the Author	32_about_the_author.md	About the Author	Background and perspective

Canonical ordering

scripts/toc_definition.py holds the table of contents and regenerates docs/book_index.json, the mkdocs.yml navigation and the chapter list in BOOK_REQUIREMENTS.md. docs/book_index.json and mkdocs.yml must agree; tests/test_book_index.py enforces that they do.