🎓 Teaching

My teaching spans deep learning, trustworthy foundation models, and the reliable deployment of modern AI systems. It follows the Auditable AI Systems program across the same four audit questions. Detection in data covers anomalies, outliers, and out-of-distribution inputs. Verification of output covers LLM evaluation, hallucination, and jailbreak detection. Auditing of action covers AI agent security, tool-call and MCP security, and audit trails. Optimization of effort covers agent efficiency, model routing, and the cost of defense training.

USC (as instructor):

• CSCI 566: Deep Learning and its Applications (Fall 2026 (scheduled); ~300 students); See Course website.
• CSCI 699: Adversarial and Trustworthy Foundation Models (Spring 2026; 40 students); See Course website.
• CSCI 566: Deep Learning and its Applications (Spring 2025; ~300 students); See Course website.
• CSCI 566: Deep Learning and its Applications (Spring 2024; ~300 students);