CYB 550 - Secure, Responsible and Trustworthy AI

Graduate standing. (4)

Investigation of the vulnerabilities of modern machine learning (ML) models and deep neural networks (DNNs), and ways to address them. Exploration of the security, privacy and trustworthiness of these systems, including topics such as adversarial machine learning, data privacy, model stealing, deepfakes, poisoning, fairness and bias mitigation, model transparency and explainability. Not open to students with credit for CYB 450. Graded ABCDE