AI Security
The model is rarely the vulnerability. The credentials, the retrieval corpus, and the tool surface are.
Who this is for
Security engineers and CISOs who have to sign off on an AI system.
What you should be able to do
Threat-model an AI system and specify the controls that let a security team approve it.
The delivery flow
The order the work actually happens in. Each step is where a decision gets made and written down, not a chapter heading.
- Asset inventory
- Threat model
- Prompt-injection surface
- Retrieval corpus controls
- Identity + scoped access
- Egress + tool limits
- Detection + logging
- Incident response
Reading path
12 published guides on this track. Every one is a live page on this site — nothing here is a placeholder.
- Cloud Security Training — Zero Trust + IAM [2026]
- AI Agent Security: Threats and Controls
- Zero Trust Security Checklist — Free — Citadel Cloud Management
- Zero Trust Security for Multi-Cloud Environments
- AI Security Architecture: Protecting LLMs, Data Pipelines, and Model Endpoints
- AI Security Framework – Free — Citadel Cloud Management
- AWS Security Audit Kit – Free — Citadel Cloud Management
- Cloud Engineering Jobs in Miami — 2026 Salary Guide | Citadel Cloud
- DevOps & DevSecOps Training for African Cloud Professionals — Citadel Cloud Management
- DevSecOps Pipeline Template – Free — Citadel Cloud Management
- Enterprise AI Security: Protecting LLMs, Agents & Data Pipelines [2026]
- How to Build a DevSecOps Pipeline from Scratch [2026 Guide]
Reference implementations
Citadel’s open-source repositories for this track — Terraform modules, MCP servers, and reference architectures you can read, fork, and run. Apache/MIT licensed; check each repository for its terms.
- GitHubterraform-aws-security-baselineAWS security baseline module with GuardDuty, Security Hub, Config, CloudTrail, Macie, and Access Analyzerterraform-aws-security-baseline on github.com (external site, opens in a new tab)
- GitHubterraform-aws-guardduty-aiAI-enhanced GuardDuty module with threat intelligence, automated triage, and Security Hub integrationterraform-aws-guardduty-ai on github.com (external site, opens in a new tab)
- GitHubai-agent-soc-triageAI-powered SOC alert triage agent with MITRE ATT&CK classification, severity scoring, and automated response playbooksai-agent-soc-triage on github.com (external site, opens in a new tab)
- GitHubterraform-aws-wafAWS WAFv2 Terraform module with managed rules, rate limiting, geoblocking, Bot Control, and loggingterraform-aws-waf on github.com (external site, opens in a new tab)
- GitHubterraform-azure-key-vaultAzure Key Vault Terraform module with RBAC, private endpoint, HSM keys, certificates, and diagnosticsterraform-azure-key-vault on github.com (external site, opens in a new tab)
Primary sources
The standards, framework documents, and vendor references this track is built against. Go here when you need the authoritative wording rather than a summary — in a security review or an audit, the source is what counts.
- OWASP Top 10 for LLM Applications (external site, opens in a new tab)
- MITRE ATLAS adversarial ML threat matrix (external site, opens in a new tab)
- NIST AI Risk Management Framework (external site, opens in a new tab)
- CIS Benchmarks (external site, opens in a new tab)
- NIST SP 800-207 Zero Trust Architecture (external site, opens in a new tab)
- CISA Secure by Design (external site, opens in a new tab)