Foundations of AI and Cybersecurity

This unit introduces core concepts of AI-driven threats and foundational cybersecurity practices needed to secure machine learning systems. Students learn to recognize common attack vectors, apply basic defensive controls, and consider ethical and privacy implications to prepare for hands-on remediation and advanced topics in later units.

Learning Objectives

• Analyze common AI and machine-learning threat vectors (e.g., adversarial examples, data poisoning, model inversion) and classify their potential impact on confidentiality, integrity, and availability
• Apply foundational cybersecurity principles (authentication, access control, secure configuration, and patch management) to propose baseline defenses for AI systems and ML pipelines
• Demonstrate identification of vulnerabilities in a simplified ML pipeline through guided, documented hands-on activities and recommend prioritized remediation steps
• Evaluate ethical, privacy, and legal considerations related to AI security incidents and recommend appropriate reporting, mitigation, and stakeholder communication strategies