About me
I am currently working as a Research Professor at Ghent University Global Campus, where my research spans several key areas at the intersection of artificial intelligence and medical applications. My current work focuses on medical and biomedical imaging, trustworthy and explainable AI, and self-supervised learning.
My interests lie in developing AI-driven solutions that enhance clinical decision-making, improve interpretability, and ensure reliability in real-world medical and biomedical settings. These days, I'm working on surgical video understanding with video object segmentation models such as SAM2 and AI-assisted characterization of sub-visible particles in biopharmaceuticals (classification, clustering, and segmentation). If you're working on cool projects within my areas of interest that I can contribute to, feel free to reach out!
My interests lie in developing AI-driven solutions that enhance clinical decision-making, improve interpretability, and ensure reliability in real-world medical and biomedical settings. These days, I'm working on surgical video understanding with video object segmentation models such as SAM2 and AI-assisted characterization of sub-visible particles in biopharmaceuticals (classification, clustering, and segmentation). If you're working on cool projects within my areas of interest that I can contribute to, feel free to reach out!
Here’s a brief overview of my career, including my current and past research focus, as well as my publications:
2023 - Current: Research Professor, Ghent University Global Campus, South Korea
Research focus
- (Med) Medical and biomedical imaging
- (XAI) Trustworthy and explainable AI
- (SSL) Image-based self-supervised learning
First author publications
- (Med) One Patient’s Annotation is Another One’s Initialization: Towards Zero-Shot Surgical Video Segmentation with Cross-Patient Initialization
2025, Arxiv - (Med) Less is More? Revisiting the Importance of Frame Rate in Real-Time Zero-Shot Surgical Video Segmentation
2025, Arxiv - (SSL) Self-Supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?
2024, IEEE IJCNN, oral presentation - (SSL) Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training
2023, Transactions on Machine Learning Research
Last and corresponding author publications
- (Med) Color Flow Imaging Microscopy Improves Identification of Stress Sources of Protein Aggregates in Biopharmaceuticals
2024, MICCAI - MOVI Workshop - (Med) Exploring Patient Data Requirements in Training Effective AI Models for MRI-based Breast Cancer Classification
2024, MICCAI - Deep Breath Workshop - (Med-XAI-SSL) Evaluating Visual Explanations of Attention Maps for Transformer-Based Medical Imaging
2024, MICCAI - iMIMIC Workshop - (Med-XAI-SSL) Identifying Critical Tokens for Accurate Predictions in Transformer-based Medical Imaging Models
2024, MICCAI - MLMI Workshop
2022 - 2023: Postdoctoral Fellow, Ghent University Global Campus, South Korea
Research focus
- (Gen) Bioinformatics and genomics
First author publications
- (Gen) Assessing the Reliability of Point Mutation as Data Augmentation for Deep Learning with Genomic Data
2024, BMC Bioinformatics - (Gen-XAI) Mutate and Observe: Utilizing Deep Neural Networks to Investigate the Impact of Mutations on Translation Initiation
2023, Bioinformatics, Oxford Press - (Gen-XAI) Utilizing Mutations to Evaluate Interpretability of Neural Networks on Genomic Data
2023, NeurIPS - LMRL Workshop - (Gen) BRCA Gene Mutations in dbSNP: A Visual Exploration of Genetic Variants
2023, Arxiv
Repositories
2017 - 2022: PhD in Computer Science, Ghent University, Belgium
Research focus
- (AISec) AI security and safety involving adversarial examples
First author publications
- (AISec) Prevalence of Adversarial Examples in Neural Networks: Attacks, Defenses, and Opportunities
2022, Ghent University, PhD thesis - (AISec-XAI) Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes
2022, NeurIPS - Workshop on ImageNet: Past, Present, and Future - (AISec-XAI) Exact Feature Collisions in Neural Networks
2022, Arxiv - (AISec) Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks
2021, BMVC, oral presentation - (AISec-XAI) Investigating the Significance of Adversarial Attacks and Their Relation to Interpretability for Radar-based Human Activity Recognition Systems
2021, Computer Vision and Image Understanding, Elsevier - (AISec) Regional Image Perturbation Reduces Lp Norms of Adversarial Examples While Maintaining Model-to-model Transferability
2020, ICML - UDL Workshop - (AISec) Perturbation Analysis of Gradient-based Adversarial Attacks
2020, Pattern Recognition Letters, Elsevier - (AISec-Med) Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation
2019, MICCAI, poster presentation - (AISec) Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding
2019, IEEE IJCNN, oral presentation - (AISec) How the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples
2018, NeurIPS - SecML Workshop
Repositories
- (XAI) github.com/utkuozbulak/pytorch-cnn-visualizations
- (AISec) github.com/utkuozbulak/adaptive-segmentation-mask-attack
- (AISec) github.com/utkuozbulak/pytorch-cnn-adversarial-attacks
- (AISec) github.com/utkuozbulak/imagenet-adversarial-image-evaluation
- (AISec) github.com/utkuozbulak/regional-adversarial-perturbation
- (Other) github.com/utkuozbulak/pytorch-custom-datasets
2016 - 2017: MSc. in Data Science, University of Southampton, UK
2015 - 2016: SAP Business Intelligence Consultant, The Coca Cola Company, Turkey
2014 - 2015: SAP Business Intelligence Consultant, Turkish Airlines, Turkey
2012 - 2014: BSc. in Computer Engineering, Yasar University, Turkey