COSC 435 AI Security Engineering with Foundation Models and Agents

This course explores the architecture, development, and security of modern AI systems, emphasizing end-to-end trustworthiness, robustness, and compliance. Topics include secure foundation models, data governance, adversarial threat modeling, MLSecOps, AI agents, and responsible AI deployment. Students are able to design and implement AI applications that prioritize integrity, privacy, and resilience against adversarial risks.

Credits

3

Prerequisite

COSC 430 and COSC 340 and COSC 434

Distribution

(3,0,3)

Offered

Fall