Research Explorer

Your browser does not support JavaScript or JavaScript is not enabled. Without JavaScript some functions of this webapplication may be disabled or cause error messages. To enable JavaScript, please consult the manual of your browser or contact your system administrator.

Researcher

Utku Özbulak

11 Results

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 ÖzbulakJasper ZuallaertStephen DepuydtJoris Vankerschaver

2021

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

Esla Timothy AnzakuUtku ÖzbulakStefan MagezArnout Van MessemWesley De Neve

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

Utku ÖzbulakArnout 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 Journal Article 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 Journal Article 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