598 citations · 2.9k across the 89 of their papers we have counts for
10 papers · 1 filter
Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet
Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko +1
Benchmark performance of deep learning classifiers alone is not a reliable predictor for the performance of a deployed model. In particular, if the image classifier has picked up s…
Diffusion Visual Counterfactual Explanations
Maximilian Augustin, Valentyn Boreiko, Francesco Croce +1
Visual Counterfactual Explanations (VCEs) are an important tool to understand the decisions of an image classifier. They are 'small' but 'realistic' semantic changes of the image c…
On the interplay of adversarial robustness and architecture components: patches, convolution and attention
Francesco Croce, Matthias Hein
In recent years novel architecture components for image classification have been developed, starting with attention and patches used in transformers. While prior works have analyze…
Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation
Maksym Yatsura, Kaspar Sakmann, N. Grace Hua +2
Adversarial patch attacks are an emerging security threat for real world deep learning applications. We present Demasked Smoothing, the first approach (up to our knowledge) to cert…
Adversarial Robustness of MR Image Reconstruction under Realistic Perturbations
Jan Nikolas Morshuis, Sergios Gatidis, Matthias Hein +1
Deep Learning (DL) methods have shown promising results for solving ill-posed inverse problems such as MR image reconstruction from undersampled -space data. However, these appr…
Provably Adversarially Robust Nearest Prototype Classifiers
Václav Voráček, Matthias Hein
Nearest prototype classifiers (NPCs) assign to each input point the label of the nearest prototype with respect to a chosen distance metric. A direct advantage of NPCs is that the…