AAISM SUCCESS BLUEPRINT

An end-to-end AI Security course designed for busy IT security and risk professionals aiming for ISACA’s AAISM certification.

This program simplifies AI security and offers a clear, guided path to success — no AI, ML, or coding background required.

ARE YOU READY TO START?

Join a growing community of forward-thinking security professionals, gain the skills to secure AI systems confidently, and ensure compliance in an AI-driven world.

Delivered through flexible, self-paced modules and supported by expert coaches, this step-by-step blueprint replaces confusion with clarity and equips you to lead in the AI era.

AAISM is designed for IT & IS Security professionals with an active CISM or CISSP certification looking to gain recognition for their expertise, assuring AI-driven processes comply to the highest industry standards.

• IT Security Professionals
• AI Governance, Risk & Compliance Experts
• AI Project Managers
• AI Consultants
• CISOs & Technology Leaders
• Professionals Pursuing Leadership in AI Security, Governance and Risk Management

Introduction to AAISM Certification

A quick intro that maps your AAISM certification path, explains the exam essentials, and highlights five clear reasons to pursue AAISM.

Preparation Strategies for AAISM Exam

Easy-to-follow concepts of memory science for active learning, smart question-solving tactics, and structured preparation strategies to get you AAISM-ready.

MODULE 1. Fundamentals of Artificial Intelligence (AI)

Gain a solid foundation in AI by exploring what it is, how it works, and the different categories of AI. This module sets the stage for deeper understanding throughout the course.

MODULE 2. Machine Learning (ML) & Its Types

Understand the core types of machine learning - supervised, unsupervised, and reinforcement learning. Learn how ML choices influence security posture, monitoring needs, and assurance expectations.

MODULE 3. Neural Networks & ML Models

Explore how neural networks work and review common ML model families used in modern AI systems. Focus on what these models imply for explainability, attack surface, and security controls across the lifecycle.

Module 4: OECD AI Development Life Cycle

Walk through the OECD AI Development Life Cycle and the key activities in each phase from planning and design to development, deployment, and monitoring.

Module 5: AI Governance, Strategy & Principles

Define how AI is governed across enterprise through clear roles, policies, and accountability. Connect ethical principles to actionable standards that align AI initiatives with business goals.

Module 6: AI Standards, Laws & Ethics

Learn the major standards and regulations shaping AI and how they translate into practical control expectations. Understand how ethics and compliance requirements influence security design, documentation, and assurance.

Module 7: AI Asset and Data Inventory

Build a complete inventory of AI assets and the underlying data they rely on, including ownership, classification, lineage, and retention.

Module 8: AI Data Management, Governance & Security Controls

Manage AI data end-to-end through governance and security controls. Reduce exposure to data-related threats such as poisoning, unauthorized use, and sensitive data disclosure.

Module 9: Developing an AI Security Program

Design a pragmatic AI security program. Align people, processes, and tools to manage risk and enable secure AI adoption.

Module 10: AI Security Architecture & Change Management

Apply secure AI security architecture and change management is mapped to enterprise environments.

Module 11: AI Incident Response Management

Adapt IR playbooks for AI incidents, from model misuse and data leakage to prompt injection and poisoning. Difference between traditional and AI-driven IR.

Module 12: AI Harms & OECD Classification

Identify common AI harms and how they manifest across safety, privacy, security, fairness, and societal impact. Use the OECD classification framework to categorize AI systems.

Module 13: Data Privacy, PETs & Supervising AI Systems

Apply privacy requirements to AI systems, including lawful basis, minimization, purpose limitation, and impact assessments. Use privacy-enhancing technologies (PETs) and human oversight to supervise outputs and reduce privacy risk.

Module 14: AI Risk Management & Frameworks

Operationalize AI risk management using leading frameworks such as NIST AI RMF, the EU AI Act risk tiers, and FAIR-based risk classification. Learn how to compare frameworks, select controls, and maintain evidence for governance and compliance.

Module 15: AI Risk Assessment Process

Scope AI systems, identify assets and threats, and evaluate likelihood/impact with control effectiveness. Produce a treatment plan with clear owners, timelines, and acceptance criteria.

Module 16: AI Threat Modeling & OWASP Top 10

Perform AI-aware threat modeling to surface abuse cases. Map controls to the OWASP Top 10 for LLM Risks (e.g., prompt injection, data leakage, insecure plugins).

Module 17: AI Testing Techniques, Threats & Vulnerabilities

Plan testing for robustness, safety, and security - unit/integration tests, adversarial testing, red teaming, and continuous evaluation. Address common vulnerabilities like poisoning, evasion, model theft, jailbreaks, and prompt leakage.

Module 18: Managing AI Vendors & Supply Chain Risks

Understand how to assess data quality in AI systems, apply analytics for audit insights, and prepare compelling reports for stakeholders.

Module 19: AI Security Controls & Monitoring

Covers key AI security controls across various categories. AI controls framework, training and continuous monitoring to detect drift and security issues.