Learning Objectives

• Apply both foundational and advanced AI concepts to support and improve an organization’s cybersecurity posture.
• Implement security controls and established best practices to protect AI systems and the data they use.
• Use AI-powered tools to improve threat detection, incident response, and automation within security operations.
• Work within global governance, risk, and compliance frameworks to support responsible and accountable AI adoption.

Course Outline

Module 1: AI and Data Fundamentals for Cybersecurity

Introduces core AI concepts and categories, generative AI and transformer architectures, machine learning and deep learning, natural language processing, AI model training methods, prompt engineering basics, security considerations for AI models, AI-related data types and data security techniques, Retrieval Augmented Generation (RAG), and controls for data integrity and processing.

Module 2: Threat Modeling and AI System Security

Examines the fundamentals of AI threat modeling, the threat modeling process and its prerequisites, applicable AI threat modeling frameworks, types of security controls for AI, model guardrails and prompt templates, gateway and interface-level controls, usage and rate-limiting controls, and methods for testing security controls.

Module 3: Access Control for AI Environments

Addresses access control principles and models as applied to AI, access controls for models and agents, API and network-level security, data security controls for AI systems, encryption and data protection measures, monitoring and logging practices for AI, performance and cost monitoring, and auditing and compliance monitoring for AI.

Module 4: AI-Specific Threats and Compensating Controls

Covers security throughout the AI lifecycle, ethical considerations in AI design, categories of AI attacks and attack techniques, backdoor and trojan attacks against models, model poisoning and model inversion, model theft, strategies for compensating controls, and post-incident analysis specific to AI systems.

Module 5: Using AI in Security Operations

Explores AI-enabled security tooling, AI applications in detection and analysis workflows, AI for vulnerability assessment, AI-enhanced attack techniques, use of AI in social engineering and deception, AI-assisted reconnaissance, AI-driven automation in security, integration of AI into DevSecOps, and AI scripting and output summarization.

Module 6: AI Governance, Risk, and Compliance

Covers governance structures for AI, organizational roles related to AI, principles of responsible AI, identifying and assessing AI-related risks, key themes in AI regulation, compliance frameworks applicable to AI, designing organizational AI policies, and producing compliance reports.