Welcome!

I am an associate professor in the department of Computer Science at Özyeğin University.

My research lies at the intersection of computer vision, machine learning, and data science, and focuses on the mathematical and learning foundations of trust-worthy AI, where robustness to unseen conditions (open-set), minimal supervision, and experimental and theoretical generalisation are investigated.

Interests: Anomaly Detection, Open-Set Recognition, Biometrics, Face Presentation Attack Detection, Deepfake Detection, Adversarial Defense, Trustworthy AI, Deep and Kernel Learning.

I serve as Associate Editor for IEEE TCSVT, and ACM Computing Surveys, and have sustained international collaborations with leading research groups (CVSSP, University of Surrey, and CSEE, University of Essex, UK).

Interests:

• Develop data/label-efficient machine learning methods targeting robustness to unseen conditions and domain shifts.

• Advance algorithmic robustness by designing methods resilient to spoofing, deepfake manipulations, and adversarial attacks.

• Translate kernel-based and one-class theoretical advances into scalable deep architectures and deployable models for visual recognition tasks.