Utku Ozbulak
Utku Ozbulak
Research Professor at Ghent University
Verified email at - Homepage
Cited by
Cited by
Impact of adversarial examples on deep learning models for biomedical image segmentation
U Ozbulak, A Van Messem, W De Neve
Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd†…, 2019
Pytorch cnn visualizations
U Ozbulak
GitHub repository, 2019
Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training
U Ozbulak, HJ Lee, B Boga, ET Anzaku, H Park, A Van Messem, ...
Transactions on Machine Learning, 2023
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems
U Ozbulak, B Vandersmissen, A Jalalvand, I Couckuyt, A Van Messem, ...
Computer Vision and Image Understanding 202, 103111, 2021
Perturbation analysis of gradient-based adversarial attacks
U Ozbulak, M Gasparyan, W De Neve, A Van Messem
Pattern Recognition Letters 135, 313-320, 2020
How the softmax output is misleading for evaluating the strength of adversarial examples
U Ozbulak, W De Neve, A Van Messem
2018 Conference on Neural Information Processing Systems (NeurIPS) Workshop†…, 2018
Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes
U Ozbulak, M Pintor, A Van Messem, W De Neve
2021 Conference on Neural Information Processing Systems (NeurIPS) Workshop†…, 2021
Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks
U Ozbulak, ET Anzaku, W De Neve, A Van Messem
2021 British Machine Vision Conference (BMVC), 2021
Automatic detection of Trypanosomosis in thick blood smears using image pre-processing and deep learning
T Jung, ET Anzaku, U ÷zbulak, S Magez, A Van Messem, W De Neve
Intelligent Human Computer Interaction: 12th International Conference, IHCI†…, 2021
Convolutional neural network visualizations
U Ozbulak, A Stoken, H Wang, R Geirhos, P Jiang
Not all adversarial examples require a complex defense: Identifying over-optimized adversarial examples with IQR-based logit thresholding
U Ozbulak, A Van Messem, W De Neve
2019 International Joint Conference on Neural Networks (IJCNN), 1-8, 2019
Regional Image Perturbation Reduces Lp Norms of Adversarial Examples While Maintaining Model-to-model Transferability
U Ozbulak, J Peck, W De Neve, B Goossens, Y Saeys, A Van Messem
2020 International Conference on Machine Learning (ICML) Workshop on†…, 2020
Tryp: a dataset of microscopy images of unstained thick blood smears for trypanosome detection
ET Anzaku, MA Mohammed, U Ozbulak, J Won, H Hong, ...
Scientific Data 10 (1), 716, 2023
Mutate and observe: utilizing deep neural networks to investigate the impact of mutations on translation initiation
U Ozbulak, HJ Lee, J Zuallaert, W De Neve, S Depuydt, J Vankerschaver
Bioinformatics 39 (6), btad338, 2023
Exact Feature Collisions in Neural Networks
U Ozbulak, M Gasparyan, S Rao, W De Neve, A Van Messem
arXiv preprint arXiv:2205.15763, 2022
Assessing the reliability of point mutation as data augmentation for deep learning with genomic data
H Lee, U Ozbulak, H Park, S Depuydt, W De Neve, J Vankerschaver
BMC bioinformatics 25 (1), 170, 2024
BRCA Gene Mutations in dbSNP: A Visual Exploration of Genetic Variants
W Jang, S Koak, J Im, U Ozbulak, J Vankerschaver
arXiv preprint arXiv:2309.00311, 2023
Utilizing Mutations to Evaluate Interpretability of Neural Networks on Genomic Data
U Ozbulak, S Kang, J Zuallaert, S Depuydt, J Vankerschaver
2022 Conference on Neural Information Processing Systems (NeurIPS) Learning†…, 2022
Prevalence of adversarial examples in neural networks: attacks, defenses, and opportunities
U ÷zbulak
Ghent University, 2022
The system can't perform the operation now. Try again later.
Articles 1–19