Course Outline
Foundations of AI and Security
- What makes AI systems unique from a security perspective
- Overview of AI lifecycle: data, training, inference, and deployment
- Basic taxonomy of AI risks: technical, ethical, legal, and organizational
AI-Specific Threat Vectors
- Adversarial examples and model manipulation
- Model inversion and data leakage risks
- Data poisoning during training phases
- Risks in generative AI (e.g., LLM misuse, prompt injection)
Security Risk Management Frameworks
- NIST AI Risk Management Framework (NIST AI RMF)
- ISO/IEC 42001 and other AI-specific standards
- Mapping AI risk to existing enterprise GRC frameworks
AI Governance and Compliance Principles
- AI accountability and auditability
- Transparency, explainability, and fairness as security-relevant properties
- Bias, discrimination, and downstream harms
Enterprise Readiness and AI Security Policies
- Defining roles and responsibilities in AI security programs
- Policy elements: development, procurement, use, and retirement
- Third-party risk and supplier AI tool usage
Regulatory Landscape and Global Trends
- Overview of the EU AI Act and international regulation
- U.S. Executive Order on Safe, Secure, and Trustworthy AI
- Emerging national frameworks and sector-specific guidance
Optional Workshop: Risk Mapping and Self-Assessment
- Mapping real-world AI use cases to NIST AI RMF functions
- Performing a basic AI risk self-assessment
- Identifying internal gaps in AI security readiness
Summary and Next Steps
Requirements
- An understanding of basic cybersecurity principles
- Experience with IT governance or risk management frameworks
- Familiarity with general AI concepts is helpful but not required
Audience
- IT security teams
- Risk managers
- Compliance professionals
Testimonials (3)
The trainer was excellent and successfully engaged the audience, even though the session was conducted remotely.
Tissier Olivier - Aesio
Course - OWASP GenAI Security
Machine Translated
inventory and identifying the different risk exposures within AI
Gary Cook - Cybersecurity and Information Technology Risk Division
Course - Introduction to AI Trust, Risk, and Security Management (AI TRiSM)
The profesional knolage and the way how he presented it before us