About me
Currently, I work as a Research Professor at the Korean Campus of Ghent University, mainly focusing on two areas: (1) image-based self-supervised learning, especially with vision transformers, and (2) explainable AI, frequently applied to biomedical imaging.
Here’s a brief overview of my career, along with my current and past research focus:
2023 - Current: Research Professor, Ghent University Global Campus, South Korea
Research focus
- (B.img) Biomedical imaging
- (XAI) Trustworthy and explainable AI
- (SSL) Image-based self-supervised learning
- (B.inf) Bioinformatics
Senior author publications
- (B.img) Color Flow Imaging Microscopy Improves Identification of Stress Sources of Protein Aggregates in Biopharmaceuticals
2024, MICCAI - MOVI Workshop - (B.img) Exploring Patient Data Requirements in Training Effective AI Models for MRI-based Breast Cancer Classification
2024, MICCAI - Deep Breath Workshop - (B.img-XAI-SSL) Evaluating Visual Explanations of Attention Maps for Transformer-Based Medical Imaging
2024, MICCAI - iMIMIC Workshop - (B.img-XAI-SSL) Identifying Critical Tokens for Accurate Predictions in Transformer-based Medical Imaging Models
2024, MICCAI - MLMI Workshop
First author publications
- (SSL) Self-Supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?
2024, IEEE IJCNN, oral presentation - (B.inf) Assessing the Reliability of Point Mutation as Data Augmentation for Deep Learning with Genomic Data
2024, BMC Bioinformatics
2022 - 2023: Postdoctoral Fellow, Ghent University Global Campus, South Korea
First author publications
- (SSL) Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training
2023, Transactions on Machine Learning Research - (B.inf) BRCA Gene Mutations in dbSNP: A Visual Exploration of Genetic Variants
2023, Arxiv - (B.inf-XAI) Mutate and Observe: Utilizing Deep Neural Networks to Investigate the Impact of Mutations on Translation Initiation
2023, Bioinformatics, Oxford Press - (B.inf-XAI) Utilizing Mutations to Evaluate Interpretability of Neural Networks on Genomic Data
2023, NeurIPS - LMRL Workshop
Repositories:
2017 - 2022: PhD in Computer Science, Ghent University, Belgium
Research focus
- (Adversarial) Adversarial examples: attacks, defenses, and properties
First author publications
- (Adversarial) Prevalence of Adversarial Examples in Neural Networks: Attacks, Defenses, and Opportunities
2022, Ghent University, PhD thesis - (Adversarial-XAI) Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes
2022, NeurIPS - Workshop on ImageNet: Past, Present, and Future - (Adversarial) Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks
2021, BMVC, oral presentation - (Adversarial-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 - (Adversarial) Regional Image Perturbation Reduces Lp Norms of Adversarial Examples While Maintaining Model-to-model Transferability
2020, ICML - UDL Workshop - (Adversarial) Perturbation Analysis of Gradient-based Adversarial Attacks
2020, Pattern Recognition Letters, Elsevier - (Adversarial-B.img) Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation
2019, MICCAI, poster presentation - (Adversarial) Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding
2019, IEEE IJCNN, oral presentation - (Adversarial) 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
- (Adversarial) github.com/utkuozbulak/adaptive-segmentation-mask-attack
- (Adversarial) github.com/utkuozbulak/pytorch-cnn-adversarial-attacks
- (Adversarial) github.com/utkuozbulak/imagenet-adversarial-image-evaluation
- (Adversarial) 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