b'Matthias Hein'

research

∙ 08/21/2023

On the Adversarial Robustness of Multi-Modal Foundation Models

Multi-modal foundation models combining vision and language models such ...

0 Christian Schlarmann, et al. ∙

research

∙ 06/22/2023

Robust Semantic Segmentation: Strong Adversarial Attacks and Fast Training of Robust Models

While a large amount of work has focused on designing adversarial attack...

0 Francesco Croce, et al. ∙

research

∙ 06/07/2023

Normalization Layers Are All That Sharpness-Aware Minimization Needs

Sharpness-aware minimization (SAM) was proposed to reduce sharpness of m...

0 Maximilian Mueller, et al. ∙

research

∙ 06/01/2023

In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation

Out-of-distribution (OOD) detection is the problem of identifying inputs...

0 Julian Bitterwolf, et al. ∙

research

∙ 03/03/2023

Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models

While adversarial training has been extensively studied for ResNet archi...

0 Naman D. Singh, et al. ∙

research

∙ 02/14/2023

A modern look at the relationship between sharpness and generalization

Sharpness of minima is a promising quantity that can correlate with gene...

0 Maksym Andriushchenko, et al. ∙

research

∙ 12/09/2022

Spurious Features Everywhere – Large-Scale Detection of Harmful Spurious Features in ImageNet

Benchmark performance of deep learning classifiers alone is not a reliab...

9 Yannic Neuhaus, et al. ∙

research

∙ 10/21/2022

Diffusion Visual Counterfactual Explanations

Visual Counterfactual Explanations (VCEs) are an important tool to under...

0 Maximilian Augustin, et al. ∙

research

∙ 09/14/2022

On the interplay of adversarial robustness and architecture components: patches, convolution and attention

In recent years novel architecture components for image classification h...

0 Francesco Croce, et al. ∙

research

∙ 09/13/2022

Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation

Adversarial patch attacks are an emerging security threat for real world...

5 Maksym Yatsura, et al. ∙

research

∙ 08/05/2022

Adversarial Robustness of MR Image Reconstruction under Realistic Perturbations

Deep Learning (DL) methods have shown promising results for solving ill-...

0 Jan Nikolas Morshuis, et al. ∙

research

∙ 07/14/2022

Sound Randomized Smoothing in Floating-Point Arithmetics

Randomized smoothing is sound when using infinite precision. However, we...

0 Václav Voráček, et al. ∙

research

∙ 07/14/2022

Provably Adversarially Robust Nearest Prototype Classifiers

Nearest prototype classifiers (NPCs) assign to each input point the labe...

0 Václav Voráček, et al. ∙

research

∙ 06/20/2022

Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities

It is an important problem in trustworthy machine learning to recognize ...

0 Julian Bitterwolf, et al. ∙

research

∙ 05/16/2022

Sparse Visual Counterfactual Explanations in Image Space

Visual counterfactual explanations (VCEs) in image space are an importan...

5 Valentyn Boreiko, et al. ∙

research

∙ 02/28/2022

Evaluating the Adversarial Robustness of Adaptive Test-time Defenses

Adaptive defenses that use test-time optimization promise to improve rob...

28 Francesco Croce, et al. ∙

research

∙ 11/02/2021

Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks

Adversarial attacks based on randomized search schemes have obtained sta...

0 Maksym Yatsura, et al. ∙

research

∙ 06/18/2021

Being a Bit Frequentist Improves Bayesian Neural Networks

Despite their compelling theoretical properties, Bayesian neural network...

0 Agustinus Kristiadi, et al. ∙

research

∙ 06/08/2021

Provably Robust Detection of Out-of-distribution Data (almost) for free

When applying machine learning in safety-critical systems, a reliable as...

0 Alexander Meinke, et al. ∙

research

∙ 05/26/2021

Adversarial robustness against multiple l_p-threat models at the price of one and how to quickly fine-tune robust models to another threat model

Adversarial training (AT) in order to achieve adversarial robustness wrt...

0 Francesco Croce, et al. ∙

research

∙ 04/16/2021

Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators

Deep neural network (DNN) accelerators received considerable attention i...

0 David Stutz, et al. ∙

research

∙ 04/09/2021

Relating Adversarially Robust Generalization to Flat Minima

Adversarial training (AT) has become the de-facto standard to obtain mod...

0 David Stutz, et al. ∙

research

∙ 03/01/2021

Mind the box: l_1-APGD for sparse adversarial attacks on image classifiers

We show that when taking into account also the image domain [0,1]^d, est...

0 Francesco Croce, et al. ∙

research

∙ 12/21/2020

Out-distribution aware Self-training in an Open World Setting

Deep Learning heavily depends on large labeled datasets which limits fur...

23 Maximilian Augustin, et al. ∙

research

∙ 10/19/2020

RobustBench: a standardized adversarial robustness benchmark

Evaluation of adversarial robustness is often error-prone leading to ove...

4 Francesco Croce, et al. ∙

research

∙ 10/06/2020

Learnable Uncertainty under Laplace Approximations

Laplace approximations are classic, computationally lightweight means fo...

0 Agustinus Kristiadi, et al. ∙

research

∙ 10/06/2020

Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features

Approximate Bayesian methods can mitigate overconfidence in ReLU network...

2 Agustinus Kristiadi, et al. ∙

research

∙ 07/16/2020

Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data

Deep neural networks are known to be overconfident when applied to out-o...

0 Julian Bitterwolf, et al. ∙

research

∙ 06/24/2020

Bit Error Robustness for Energy-Efficient DNN Accelerators

Deep neural network (DNN) accelerators received considerable attention i...

0 David Stutz, et al. ∙

research

∙ 06/23/2020

Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks

A large body of research has focused on adversarial attacks which requir...

0 Francesco Croce, et al. ∙

research

∙ 03/20/2020

Adversarial Robustness on In- and Out-Distribution Improves Explainability

Neural networks have led to major improvements in image classification b...

4 Maximilian Augustin, et al. ∙

research

∙ 03/03/2020

Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks

The field of defense strategies against adversarial attacks has signific...

0 Francesco Croce, et al. ∙

research

∙ 02/24/2020

Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks

The point estimates of ReLU classification networks—arguably the most wi...

0 Agustinus Kristiadi, et al. ∙

research

∙ 02/06/2020

Computing the norm of nonnegative matrices and the log-Sobolev constant of Markov chains

We analyze the global convergence of the power iterates for the computat...

0 Antoine Gautier, et al. ∙

research

∙ 11/29/2019

Square Attack: a query-efficient black-box adversarial attack via random search

We propose the Square Attack, a new score-based black-box l_2 and l_∞ ad...

0 Maksym Andriushchenko, et al. ∙

research

∙ 10/30/2019

Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs

We study the task of semi-supervised learning on multilayer graphs by ta...

10 Pedro Mercado, et al. ∙

research

∙ 10/14/2019

Confidence-Calibrated Adversarial Training: Towards Robust Models Generalizing Beyond the Attack Used During Training

Adversarial training is the standard to train models robust against adve...

0 David Stutz, et al. ∙

research

∙ 09/26/2019

Towards neural networks that provably know when they don't know

It has recently been shown that ReLU networks produce arbitrarily over-c...

0 Alexander Meinke, et al. ∙

research

∙ 09/11/2019

Sparse and Imperceivable Adversarial Attacks

Neural networks have been proven to be vulnerable to a variety of advers...

10 Francesco Croce, et al. ∙

research

∙ 07/03/2019

Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack

The evaluation of robustness against adversarial manipulation of neural ...

0 Francesco Croce, et al. ∙

research

∙ 06/08/2019

Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks

The problem of adversarial samples has been studied extensively for neur...

0 Maksym Andriushchenko, et al. ∙

research

∙ 05/27/2019

Provable robustness against all adversarial l_p-perturbations for p≥ 1

In recent years several adversarial attacks and defenses have been propo...

0 Francesco Croce, et al. ∙

research

∙ 05/15/2019

Spectral Clustering of Signed Graphs via Matrix Power Means

Signed graphs encode positive (attractive) and negative (repulsive) rela...

0 Pedro Mercado, et al. ∙

research

∙ 03/27/2019

Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks

Modern neural networks are highly non-robust against adversarial manipul...

0 Francesco Croce, et al. ∙

research

∙ 12/13/2018

Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem

Classifiers used in the wild, in particular for safety-critical systems,...

52 Matthias Hein, et al. ∙

research

∙ 12/03/2018

Disentangling Adversarial Robustness and Generalization

Obtaining deep networks that are robust against adversarial examples and...

0 David Stutz, et al. ∙

research

∙ 11/28/2018

A randomized gradient-free attack on ReLU networks

It has recently been shown that neural networks but also other classifie...

0 Francesco Croce, et al. ∙

research

∙ 10/29/2018

Logit Pairing Methods Can Fool Gradient-Based Attacks

Recently, several logit regularization methods have been proposed in [Ka...

0 Marius Mosbach, et al. ∙

research

∙ 10/17/2018

Provable Robustness of ReLU networks via Maximization of Linear Regions

It has been shown that neural network classifiers are not robust. This r...

0 Francesco Croce, et al. ∙

research

∙ 09/27/2018

On the loss landscape of a class of deep neural networks with no bad local valleys

We identify a class of over-parameterized deep neural networks with stan...

0 Quynh Nguyen, et al. ∙

Matthias Hein

Featured Co-authors