| Explores the intersection of machine learning and security, focusing on adversarial techniques and defenses. Students will learn about the various types of adversarial attacks on machine learning models, the theoretical foundations of adversarial machine learning and secure Al, and practical strategies for defending against these attacks. Through a combination of lectures, hands-on projects, and case studies, students will gain a comprehensive understanding of the security vulnerabilities and challenges in machine learning models and Al systems and how to address them. Participants should be comfortable with the basics of mathematics, linear algebra, statistics and probability. Programming skills are required in Python or R. Some practical examples and applications will be presented in Python. Basic knowledge of machine learning and deep learning is strongly recommended. |
