Introduction to AI Security and Risk Management Training Course

Foundations of Artificial Intelligence (AI) and Security

• Characteristics that distinguish AI systems from a security standpoint
• Overview of the AI lifecycle: data collection, training, inference, and deployment
• Basic classification of AI risks: technical, ethical, legal, and organizational

AI-Specific Threat Vectors

• Adversarial examples and model manipulation techniques
• Model inversion and associated data leakage vulnerabilities
• Data poisoning during the training phase
• Risks in generative AI, including misuse of large language models (LLMs) and prompt injection

Security Risk Management Frameworks for Government

• NIST Artificial Intelligence Risk Management Framework (NIST AI RMF)
• ISO/IEC 42001 and other AI-specific standards
• Integrating AI risk into existing enterprise governance, risk management, and compliance (GRC) frameworks

AI Governance and Compliance Principles for Government

• Ensuring accountability and auditability in AI systems
• Promoting transparency, explainability, and fairness as critical security properties
• Addressing bias, discrimination, and downstream consequences

Enterprise Readiness and AI Security Policies for Government

• Establishing roles and responsibilities within AI security programs
• Key policy components: development, procurement, use, and retirement of AI systems
• Managing third-party risks and the use of supplier AI tools

Regulatory Landscape and Global Trends for Government

• Overview of the EU Artificial Intelligence Act and international regulatory developments
• U.S. Executive Order on Safe, Secure, and Trustworthy AI
• Emerging national frameworks and sector-specific guidance for government

Optional Workshop: Risk Mapping and Self-Assessment

• Mapping real-world AI use cases to NIST AI RMF functions
• Conducting a basic AI risk self-assessment
• Identifying internal gaps in AI security readiness for government operations

Summary and Next Steps for Government