Instellingen beheren
MENU
Over deze site
In English
Home
Onderzoekers
Projecten
Organisaties
Publicaties
Contact
Research Explorer
Uw browser ondersteunt geen JavaScript of JavaScript is niet ingeschakeld. Zonder JavaScript kan sommige functionaliteit van deze webapplicatie uitgeschakeld zijn of foutmeldingen veroorzaken. Raadpleeg om JavaScript in te schakelen de handleiding van uw browser of contacteer uw systeembeheerder.
Onderzoeker
Utku Özbulak
Profiel
Projecten
Publicaties
Activiteiten
Prijzen & Erkenningen
11
Resultaten
2022
Prevalence of adversarial examples in neural networks : attacks, defenses, and opportunities
Utku Özbulak
Wesley De Neve
Arnout Van Messem
Proefschrift
2022
Utilizing mutations to evaluate interpretability of neural networks on genomic data
Utku Özbulak
Solha Kang
Jasper Zuallaert
Stephen Depuydt
Joris Vankerschaver
C1
Conferentie
2022
2021
Automatic detection of Trypanosomosis in thick blood smears using image pre-processing and deep learning
Taewoo Jung
Esla Timothy Anzaku
Utku Özbulak
Stefan Magez
Arnout Van Messem
Wesley De Neve
P1
Conferentie
2021
Evaluating adversarial attacks on ImageNet : a reality check on misclassification classes
Utku Özbulak
Maura Pintor
Arnout Van Messem
Wesley De Neve
C1
Conferentie
2021
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems
Utku Özbulak
Baptist Vandersmissen
Azarakhsh Jalalvand
Ivo Couckuyt
Arnout Van Messem
Wesley De Neve
A1
Artikel in een tijdschrift
in
COMPUTER VISION AND IMAGE UNDERSTANDING
2021
Selection of source images heavily influences the effectiveness of adversarial attacks
Utku Özbulak
Esla Timothy Anzaku
Wesley De Neve
Arnout Van Messem
C1
Conferentie
2021
2020
Perturbation analysis of gradient-based adversarial attacks
Utku Özbulak
Manvel Gasparyan
Wesley De Neve
Arnout Van Messem
A1
Artikel in een tijdschrift
in
PATTERN RECOGNITION LETTERS
2020
Regional image perturbation reduces Lp norms of adversarial examples while maintaining model-to-model transferability
Utku Özbulak
Jonathan Peck
Wesley De Neve
Bart Goossens
Yvan Saeys
Arnout Van Messem
C1
Conferentie
2020
2019
Impact of adversarial examples on deep learning models for biomedical image segmentation
Utku Özbulak
Arnout Van Messem
Wesley De Neve
P1
Conferentie
2019
Not all adversarial examples require a complex defense : identifying over-optimized adversarial examples with IQR-based logit thresholding
Utku Özbulak
Arnout Van Messem
Wesley De Neve
P1
Conferentie
2019
2018
How the Softmax output is misleading for evaluating the strength of adversarial examples
Utku Özbulak
Wesley De Neve
Arnout Van Messem
C1
Conferentie
2018