Research, teaching, and projects
A broader view of my work.
This general CV highlights my work in trustworthy AI, LLM safety and security, machine unlearning, interpretability, secure agentic AI, reproducibility, and explainable AI for health.
It also includes my experience with multimodal models, anomaly detection, and vision-language adaptation as supporting research areas.
Updated August 2026: ERUF accepted to EMNLP 2026 Findings.