AI Security Data Privacy

3 Credits · Level: Graduate

This course offers a comprehensive overview of the essential practices of securing AI systems and protecting data. The first part of the course focuses on the security threats unique to AI, including adversarial attacks, data poisoning, and model theft. Students will learn about the techniques used to exploit AI systems and the strategies to defend against these threats. This includes best practices in securing AI data, algorithms, and infrastructures. The second part of the course examines the core concepts of privacy, including data confidentiality, integrity, and the rights of individuals regarding their personal information. Students will explore issues such as data surveillance, profiling, and the potential for AI to infringe on personal privacy. Students will learn about various scenarios where AI's data processing capabilities might conflict with privacy norms and expectations. Practical strategies for preserving privacy in AI systems form a key part of the curriculum. Students will explore techniques such as anonymization, data minimization, and secure data storage.