ARI 361 AI Security and Adversarial Machine Learning
This course focuses on the principles and practices of securing artificial intelligence systems. Students will have the opportunity to examine threats to AI models and data, including adversarial attacks, data poisoning, model inversion, and prompt injection. The course also explores strategies for building robust, privacy-preserving, and trustworthy AI systems, with attention to both technical defenses and operational safeguards.
Prerequisite: ARI 306 and MAT 203