I am a researcher in Explainable AI (XAI) at The AI Lab at The American College of Greece, where I hold a BSc (Hons) in Cybersecurity & Networking. In Fall 2026, I will be joining a PhD program with a focus on Human-Centered Explainable AI (HCXAI).

My work addresses the explainability and trustworthiness of AI systems — specifically over-reliance, non-interpretable outputs, and hallucinations in healthcare and other real-world applications.

Under the supervision of Prof. Ioannis T. Christou, I am developing computer vision models for early diagnosis of acute lymphoblastic leukemia, applying Grad-CAM to interpret and validate learned representations. Concurrently, my thesis — COMPASS: Benchmarking Safety-Aware Navigation for Vision Language Models — evaluates the safety-alignment of vision-language models against established guidelines.