Introduction to AI Security: Concepts and Lifecycle Risks, Threat Modeling in AI Systems, Adversarial Machine Learning Fundamentals, Red-Teaming AI: Attack Techniques and Tools, Case Studies in Model Exploitation, Data Poisoning and Input Manipulation, Midterm Exam, Blue-Teaming AI: Defensive Approaches, Secure Model Training and Robustness Techniques, AI-Specific Risk Assessment Frameworks, Explainability and Security Intersections, Final Project Presentations, Review and Advanced Topics.