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

11 Resultaten

2022

Prevalence of adversarial examples in neural networks : attacks, defenses, and opportunities

Utku ÖzbulakWesley De NeveArnout Van Messem

Utilizing mutations to evaluate interpretability of neural networks on genomic data

Utku ÖzbulakSolha KangJasper ZuallaertStephen DepuydtJoris Vankerschaver

2021

Automatic detection of Trypanosomosis in thick blood smears using image pre-processing and deep learning

Taewoo JungEsla Timothy AnzakuUtku ÖzbulakStefan MagezArnout Van MessemWesley De Neve

Evaluating adversarial attacks on ImageNet : a reality check on misclassification classes

Utku ÖzbulakMaura PintorArnout Van MessemWesley De Neve

Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems

Utku ÖzbulakBaptist VandersmissenAzarakhsh JalalvandIvo CouckuytArnout Van MessemWesley De Neve

A1 Artikel in een tijdschrift in COMPUTER VISION AND IMAGE UNDERSTANDING

Selection of source images heavily influences the effectiveness of adversarial attacks

Utku ÖzbulakEsla Timothy AnzakuWesley De NeveArnout Van Messem

2020

Perturbation analysis of gradient-based adversarial attacks

Utku ÖzbulakManvel GasparyanWesley De NeveArnout Van Messem

A1 Artikel in een tijdschrift in PATTERN RECOGNITION LETTERS

Regional image perturbation reduces Lp norms of adversarial examples while maintaining model-to-model transferability

Utku ÖzbulakJonathan PeckWesley De NeveBart GoossensYvan SaeysArnout Van Messem

2019

Impact of adversarial examples on deep learning models for biomedical image segmentation

Utku ÖzbulakArnout Van MessemWesley De Neve

Not all adversarial examples require a complex defense : identifying over-optimized adversarial examples with IQR-based logit thresholding

Utku ÖzbulakArnout Van MessemWesley De Neve

2018

How the Softmax output is misleading for evaluating the strength of adversarial examples

Utku ÖzbulakWesley De NeveArnout Van Messem