The AI Security course has 16 modules in two parts. In Part 1 you understand and attack AI systems. In Part 2 you defend and govern them on Azure. Every module pairs short theory with a hands-on lab. This guide walks through the syllabus.
Module 1: Introduction to AI Security and Architecture Layers
Understand what is different about securing AI systems and map where attackers can strike.
- What AI security is and why it matters, with the CIA triad applied to AI and LLMs
- The layers of an AI application: model, application, data, orchestration and infrastructure
- The attack surface and the OWASP Top 10 for LLM Applications
Module 2: Prompt Injection and Jailbreaking
See how instructions hidden in user input or in content the model reads can take over its behaviour.
- Direct and indirect prompt injection, including poisoned web pages, documents and emails
- Jailbreak techniques: role-play, instruction override, encoding and obfuscation
- Why guardrails fail
Module 3: Model Manipulation and Data Exfiltration
Learn how models leak what they were told to protect and how attackers move data out.
- Training-data poisoning, model inversion and membership inference at concept level
- Sensitive-data disclosure and system-prompt leakage
- Data exfiltration through indirect injection, such as malicious markdown image URLs
Module 4: AI Overreliance and Introduction to AI Red Teaming
Understand the risk of trusting model output and how red teaming tests AI systems.
- Overreliance, hallucination and insecure output handling
- What AI red teaming is: security, safety and responsible-AI testing
- How AI red teaming differs from traditional penetration testing
Module 5: AI Red Teaming Methodology and Planning
Plan an AI engagement like a professional: scope, threats and test cases.
- Scoping, objectives and rules of engagement
- Threat-modelling an AI system
- MITRE ATLAS for adversarial AI tactics
Module 6: Automated Red Teaming with garak
Use an open-source LLM vulnerability scanner to test models at scale.
- What garak is and how probes and detectors work
- Probes for prompt injection, jailbreaks, toxicity and data leakage
- Running scans against local and hosted models
Module 7: Microsoft PyRIT: Python Risk Identification Tool
Automate attacks and scoring with the framework Microsoft's AI Red Team uses.
- PyRIT overview and architecture
- Orchestrators, targets, converters and scorers
- Automating multi-turn attacks
Module 8: Content-Filter Bypass and Reporting
Understand why filters fail and how to report an AI finding so it gets fixed.
- Techniques for bypassing guardrails and content filters, and why they work
- Structuring an AI red-team report: finding, impact, evidence and fix
- Moving from attacker mindset to defender mindset
Module 9: AI Security Controls
Start defending: the controls that reduce the risks you just exploited.
- Reviewing open-source AI libraries securely
- Content filters, metaprompts and system prompts, and grounding with RAG
- AI data security and application-security best practices
Module 10: Azure AI Content Safety
Use managed safety services to detect harmful content and attacks.
- Categories (hate, sexual, violence, self-harm) and severity levels
- Prompt Shields for jailbreak detection, groundedness detection and protected-material checks
- Risk and safety evaluation of text and image content
Module 11: Secure Azure AI Services: Authentication and Network
Control who and what can reach your AI endpoints.
- API keys versus Microsoft Entra ID and managed identity
- Private endpoints, firewall rules and disabling public access
- End-to-end management of Azure AI Services security
Module 12: Security Recommendations for AI Workloads
Protect AI resources, models, access and execution as one system.
- Securing AI resources, models, access and execution
- Least-privilege RBAC and secrets management
- Guarding the model supply chain and the deployment pipeline
Module 13: Azure AI Security Features, Part 1
Protect data in transit and manage credentials safely.
- Transport Layer Security for AI endpoints
- Authentication options and key rotation
- Using environment variables to keep secrets out of code
Module 14: Azure AI Security Features, Part 2
Add stronger data protection and isolation.
- Customer-managed keys and virtual networks
- Data loss prevention and Customer Lockbox
- Bring Your Own Storage
Module 15: Monitoring, Abuse Monitoring and Responsible AI
See what is happening in production and govern AI responsibly.
- Monitoring Azure OpenAI Service
- Building generative-AI workloads with the Well-Architected Framework
- Abuse monitoring and content-filtering systems
Module 16: Trustworthy AI, Data Privacy and Capstone
Bring everything together in an end-to-end hardened and tested deployment.
- Microsoft Trustworthy AI: security, privacy and safety
- What data Azure OpenAI processes, how it is processed and how to verify abuse-monitoring storage settings
- Residual-risk assessment and remediation planning
By the End
You will be able to explain the AI and LLM attack surface, perform and report attacks in a lab, run automated red teaming with garak and PyRIT, and secure Azure AI services with managed identity, private endpoints, RBAC and Key Vault.
