24 citations · 38 across the 8 of their papers we have counts for
8 papers
The Impact of the Single-Label Assumption in Image Recognition Benchmarking
Esla Timothy Anzaku, Seyed Amir Mousavi, Arnout Van Messem +1
Deep neural networks (DNNs) are typically evaluated under the assumption that each image has a single correct label. However, many images in benchmarks like ImageNet contain multip…
A Principled Evaluation Protocol for Comparative Investigation of the Effectiveness of DNN Classification Models on Similar-but-non-identical Datasets
Esla Timothy Anzaku, Haohan Wang, Arnout Van Messem +1
Deep Neural Network (DNN) models are increasingly evaluated using new replication test datasets, which have been carefully created to be similar to older and popular benchmark data…
Exact Feature Collisions in Neural Networks
Utku Ozbulak, Manvel Gasparyan, Shodhan Rao +2
Predictions made by deep neural networks were shown to be highly sensitive to small changes made in the input space where such maliciously crafted data points containing small pert…
Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes
Utku Ozbulak, Maura Pintor, Arnout Van Messem +1
Although ImageNet was initially proposed as a dataset for performance benchmarking in the domain of computer vision, it also enabled a variety of other research efforts. Adversaria…
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems
Utku Ozbulak, Baptist Vandersmissen, Azarakhsh Jalalvand +3
Given their substantial success in addressing a wide range of computer vision challenges, Convolutional Neural Networks (CNNs) are increasingly being used in smart home application…
Regional Image Perturbation Reduces Norms of Adversarial Examples While Maintaining Model-to-model Transferability
Utku Ozbulak, Jonathan Peck, Wesley De Neve +3
Regional adversarial attacks often rely on complicated methods for generating adversarial perturbations, making it hard to compare their efficacy against well-known attacks. In thi…