Welcome to the website of Shervin R. Arashloo!

I am a faculty member in the Department of Computer Engineering at Bilkent University, specialising in trustworthy visual AI, with a focus on one-class classification, deep kernel learning, and biometric security.

I serve as Associate Editor for the Pattern Recognition and Neurocomputing journals, and have sustained international collaborations with leading research groups (CVSSP, University of Surrey, UK).

My research focuses on advancing secure, deployable machine learning systems through interdisciplinary projects.

Interests:

• Develop data-efficient machine learning methods for security and anomaly detection, targeting robustness to unseen conditions and domain shifts.

• Advance forensic robustness by designing algorithms resilient to spoofing, adversarial attacks, and deepfake manipulations.

• Translate kernel-based and one-class theoretical advances into scalable deep architectures and deployable models for forensic applications.