About me

I'm currently working as a Research Professor at Ghent University Global Campus (GUGC) and an Adjunct Professor at George Mason University Korea (GMUK), currently teaching Data Visualization at GMUK and Bioinformatics at GUGC.

These days, I'm working on automated machine learning research for vision problems, AI-assisted characterization of sub-visible particles in biopharmaceuticals and general vision problems involving medical and biomedical imaging, some topics involving spurious correlations, robust predictions, and interpretable AI. 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 education, work history, research focus (past and present), publications, and repositories.

News

08/26 - Our paper introducing a curated dataset of subvisible protein particles from monoclonal antibodies was published in Scientific Data. [Link]

07/26 - Our paper on tokenizer scale in SMILES-based molecular foundation models was accepted at the International Conference on AI in Healthcare (AIiH 2026). [Link]

06/26 - Our paper on SMILES-based bioactivity prediction through molecular encoder selection and data augmentation was published in Journal of Cheminformatics. [Link]

Summary

Current Positions:

  • Research Professor at Ghent University Global Campus, South Korea
  • Adjunct Professor at George Mason University Korea, South Korea

Education:

  • PhD in Computer Science Engineering, Ghent University, Belgium
  • MSc in Data Science, University of Southampton, United Kingdom
  • BSc in Computer Engineering, Yasar University, Turkey
Work Experience

2025 - Current: Adjunct Professor, George Mason Korea, South Korea

2023 - Current: Research Professor, Ghent University Global Campus, South Korea

2022 - 2023: Postdoctoral Fellow, Ghent University Global Campus, South Korea

2017 - 2022: AI Researcher, Ghent University Global Campus, South Korea

2015 - 2016: SAP Business Intelligence Consultant, The Coca Cola Company, Turkey

2014 - 2015: SAP Business Intelligence Consultant, Turkish Airlines, Turkey

Research Expertise

(Biomed) Medical and biomedical imaging

(XAI) Trustworthy and explainable AI

(Bioinf) Bioinformatics, genomics, and drug discovery

(SecureAI) AI security and safety

(SSL) Image-based self-supervised learning

Publications
First or Corresponding Author Publications

(Biomed) A Curated Flow Imaging Microscopy Dataset of Subvisible Protein Aggregates from Stressed Monoclonal Antibodies
Utku Ozbulak, Michaela Cohrs, Hristo L. Svilenov, Wesley De Neve
2026, Scientific Data, Nature Publishing [Link]

(SSL-XAI) Token-Based Detection of Spurious Correlations in Vision Transformers
Solha Kang, Esla Timothy Anzaku, Wesley De Neve, Arnout Van Messem, Joris Vankerschaver, Francois Rameau, Utku Ozbulak
2026, Transactions on Machine Learning Research [Link]

(Biomed) Token-based Fidelity Scoring for Trustworthy Vision Transformer Interpretations in Medical Imaging
Utku Ozbulak, Solha Kang, Wesley De Neve, Joris Vankerschaver
2026, International Journal of Computer Assisted Radiology and Surgery, Springer Nature [Link]

(Biomed) Improved Sub-visible Particle Classification in Flow Imaging Microscopy via Generative AI-based Image Synthesis
Utku Ozbulak, Michaela Cohrs, Hristo L. Svilenov, Joris Vankerschaver, Wesley De Neve
2026, Journal of Pharmaceutical Sciences, Elsevier [Link]

(SecureAI) Exact Feature Collisions in Neural Networks
Utku Ozbulak, Shodhan Rao, Wesley De Neve, Joris Vankerschaver, Arnout Van Messem, Manvel Gasparyan
2026, Scientific Reports, Nature Publishing [Link]

(Med) Revisiting the Evaluation Bias Introduced by Frame Sampling Strategies in Surgical Video Segmentation Using SAM2
Utku Ozbulak, Seyed Amir Mousavi, Francesca Tozzi, Niki Rashidian, Wouter Willaert, Wesley De Neve
2025, MICCAI - FAMI Workshop [Link]

(Biomed) SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-world Breast MRI Classification
Jong Bum Won, Wesley De Neve, Joris Vankerschaver, Utku Ozbulak
2025, MICCAI - Main Track - Early Accept [Link]

(Biomed) When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videos
Woowon Jang, Jiwon Im, Juseung Choi, Niki Rashidian, Wesley De Neve, Utku Ozbulak
2025, MICCAI - COLAS Workshop [Link]

(Med) Towards Affordable Tumor Segmentation and Visualization for 3D Breast MRI Using SAM2
Solha Kang, Eugene Kim, Joris Vankerschaver, Utku Ozbulak
2025, MICCAI - Deep Breath Workshop [Link]

(Bioinf) Assessing the Reliability of Point Mutation as Data Augmentation for Deep Learning with Genomic Data
Hyunjung Lee, Utku Ozbulak*, Homin Park, Stephen Depuydt, Wesley De Neve, Joris Vankerschaver
2024, BMC Bioinformatics [Link]

(SSL) Self-Supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?
Utku Ozbulak, Esla Timothy Anzaku, Solha Kang, Wesley De Neve, Joris Vankerschaver
2024, IEEE IJCNN, oral presentation [Link]

(Biomed) Color Flow Imaging Microscopy Improves Identification of Stress Sources of Protein Aggregates in Biopharmaceuticals
Michaela Cohrs, Shiwoo Koak, Yejin Lee, Yu Jin Sung, Wesley De Neve, Hristo L. Svilenov, Utku Ozbulak
2024, MICCAI - MOVI Workshop [Link]

(Biomed) Exploring Patient Data Requirements in Training Effective AI Models for MRI-based Breast Cancer Classification
Solha Kang, Wesley De Neve, Francois Rameau, Utku Ozbulak
2024, MICCAI - Deep Breath Workshop [Link]

(Biomed-XAI-SSL) Evaluating Visual Explanations of Attention Maps for Transformer-Based Medical Imaging
Minjae Chung, Jong Bum Won, Ganghyun Kim, Yujin Kim, Utku Ozbulak
2024, MICCAI - iMIMIC Workshop [Link]

(Biomed-XAI-SSL) Identifying Critical Tokens for Accurate Predictions in Transformer-based Medical Imaging Models
Solha Kang, Joris Vankerschaver, Utku Ozbulak
2024, MICCAI - MLMI Workshop [Link]

(Bioinf-XAI) Utilizing Mutations to Evaluate Interpretability of Neural Networks on Genomic Data
Utku Ozbulak, Solha Kang, Jasper Zuallaert, Stephen Depuydt, Joris Vankerschaver
2023, NeurIPS - LMRL Workshop [Link]

(Bioinf-XAI) Mutate and Observe: Utilizing Deep Neural Networks to Investigate the Impact of Mutations on Translation Initiation
Utku Ozbulak, Hyun Jung Lee, Jasper Zuallaert, Wesley De Neve, Stephen Depuydt, Joris Vankerschaver
2023, Bioinformatics, Oxford Press [Link]

(SSL) Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training
Utku Ozbulak, Hyun Jung Lee, Beril Boga, Esla Timothy Anzaku, Homin Park, Arnout Van Messem, Wesley De Neve, Joris Vankerschaver
2023, Transactions on Machine Learning Research [Link]

(SecureAI-XAI) Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes
Utku Ozbulak, Maura Pintor, Arnout Van Messem, Wesley De Neve
2022, NeurIPS - Workshop on ImageNet: Past, Present, and Future [Link]

(SecureAI) Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks
Utku Ozbulak, Esla Timothy Anzaku, Wesley De Neve, Arnout Van Messem
2021, BMVC, oral presentation [Link]

(SecureAI-XAI) Investigating the Significance of Adversarial Attacks and Their Relation to Interpretability for Radar-based Human Activity Recognition Systems
Utku Ozbulak, Baptist Vandersmissen, Azarakhsh Jalalvand, Ivo Couckuyt, Arnout Van Messem, Wesley De Neve
2021, Computer Vision and Image Understanding, Elsevier [Link]

(SecureAI) Regional Image Perturbation Reduces Lp Norms of Adversarial Examples While Maintaining Model-to-model Transferability
Utku Ozbulak, Jonathan Peck, Wesley De Neve, Bart Goossens, Yvan Saeys, Arnout Van Messem
2020, ICML - UDL Workshop [Link]

(SecureAI) Perturbation Analysis of Gradient-based Adversarial Attacks
Utku Ozbulak, Manvel Gasparyan, Wesley De Neve, Arnout Van Messem
2020, Pattern Recognition Letters, Elsevier [Link]

(SecureAI-Med) Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation
Utku Ozbulak, Arnout Van Messem, Wesley De Neve
2019, MICCAI, poster presentation [Link]

(SecureAI) Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding
Utku Ozbulak, Arnout Van Messem, Wesley De Neve
2019, IEEE IJCNN, oral presentation [Link]

(SecureAI) How the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples
Utku Ozbulak, Wesley De Neve, Arnout Van Messem
2018, NeurIPS - SecML Workshop [Link]

Other Publications

(Bioinf) A Controlled Study of Tokenizer Scale in SMILES-Based Foundation Models
Seongik Choi, Ju Hyung Lee, Utku Ozbulak, Joris Vankerschaver, Wesley De Neve
2026, International Conference on AI in Healthcare (AIiH), Springer Nature [Link]

(Bioinf) Smiles-based bioactivity prediction through molecular encoder selection and data augmentation
Ju Hyung Lee, Seongik Choi, Utku Ozbulak, Joris Vankerschaver, Wesley De Neve
2026, Journal of Cheminformatics [Link]

(SecureAI) Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression
Oleksii Nasypanyi, Jaemin Cho, Utku Ozbulak, Byungkon Kang, Francois Rameau
2026, ECCV [Link]

(Biomed) Predicting Agitation Stability of Monoclonal Antibodies during Developability Assessment
Michaela Cohrs, Nevena Pagureva, Utku Ozbulak, Wesley De Neve, Kevin Braeckmans, Stefaan De Smedt, Slavka Tcholakova, Zahari Vinarov, Hristo L. Svilenov
2026, Molecular Pharmaceutics [Link]

(Biomed) Balancing Redundancy and Diversity: An In-Depth Analysis of Active Learning for Laparoscopic Video Segmentation
Seyed Amir Mousavi, Esla Timothy Anzaku, Utku Ozbulak, Robbe De Muynck, Francesca Tozzi, Nikdokht Rashidian, Wouter Willaert, Wesley De Neve
2025, MICCAI - DEMI Workshop [Link]

(Med) One Patient's Annotation is Another One's Initialization: Towards Zero-Shot Surgical Video Segmentation with Cross-Patient Initialization
Seyed Amir Mousavi, Utku Ozbulak, Francesca Tozzi, Nikdokht Rashidian, Wouter Willaert, Joris Vankerschaver, Wesley De Neve
2025, Arxiv [Link]

(Bioinf) BRCA Gene Mutations in dbSNP: A Visual Exploration of Genetic Variants
Woowon Jang, Shiwoo Koak, Jiwon Im, Utku Ozbulak, Joris Vankerschaver
2023, Arxiv [Link]

(Biomed) Tryp: A Dataset of Microscopy Images of Unstained Thick Blood Smears for Trypanosome Detection
Esla Timothy Anzaku, Mohammed Aliy Mohammed, Utku Ozbulak, Jongbum Won, Hyesoo Hong, Janarthanan Krishnamoorthy, Sofie Van Hoecke, Stefan Magez, Arnout Van Messem, Wesley De Neve
2023, Scientific Data, Nature Publishing [Link]

(Bioinf-Med) Automatic Detection of Trypanosomosis in Thick Blood Smears Using Image Pre-processing and Deep Learning
Taewoo Jung, Esla Timothy Anzaku, Utku Ozbulak, Stefan Magez, Arnout Van Messem, Wesley De Neve
2021, International Conference on Intelligent Human Computer Interaction (IHCI) [Link]

Repositories