Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Matthias Hein

Matthias Hein

University of Tübingen

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


Apr 16, 2021
David Stutz, Nandhini Chandramoorthy, Matthias Hein, Bernt Schiele

* arXiv admin note: substantial text overlap with arXiv:2006.13977 

  Access Paper or Ask Questions

Relating Adversarially Robust Generalization to Flat Minima


Apr 09, 2021
David Stutz, Matthias Hein, Bernt Schiele


  Access Paper or Ask Questions

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


Mar 01, 2021
Francesco Croce, Matthias Hein


  Access Paper or Ask Questions

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


Dec 21, 2020
Maximilian Augustin, Matthias Hein


  Access Paper or Ask Questions

RobustBench: a standardized adversarial robustness benchmark


Oct 19, 2020
Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Nicolas Flammarion, Mung Chiang, Prateek Mittal, Matthias Hein


  Access Paper or Ask Questions

Learnable Uncertainty under Laplace Approximations


Oct 06, 2020
Agustinus Kristiadi, Matthias Hein, Philipp Hennig


  Access Paper or Ask Questions

Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features


Oct 06, 2020
Agustinus Kristiadi, Matthias Hein, Philipp Hennig


  Access Paper or Ask Questions

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


Jul 16, 2020
Julian Bitterwolf, Alexander Meinke, Matthias Hein

* Code available at https://gitlab.com/Bitterwolf/GOOD 

  Access Paper or Ask Questions

On Mitigating Random and Adversarial Bit Errors


Jun 24, 2020
David Stutz, Nandhini Chandramoorthy, Matthias Hein, Bernt Schiele


  Access Paper or Ask Questions

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


Jun 23, 2020
Francesco Croce, Maksym Andriushchenko, Naman D. Singh, Nicolas Flammarion, Matthias Hein


  Access Paper or Ask Questions

Adversarial Robustness on In- and Out-Distribution Improves Explainability


Mar 20, 2020
Maximilian Augustin, Alexander Meinke, Matthias Hein


  Access Paper or Ask Questions

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


Mar 03, 2020
Francesco Croce, Matthias Hein


  Access Paper or Ask Questions

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


Feb 24, 2020
Agustinus Kristiadi, Matthias Hein, Philipp Hennig


  Access Paper or Ask Questions

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


Nov 29, 2019
Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion, Matthias Hein


  Access Paper or Ask Questions

Confidence-Calibrated Adversarial Training and Detection: More Robust Models Generalizing Beyond the Attack Used During Training


Nov 25, 2019
David Stutz, Matthias Hein, Bernt Schiele


  Access Paper or Ask Questions

Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs


Oct 30, 2019
Pedro Mercado, Francesco Tudisco, Matthias Hein

* Accepted in NeurIPS 2019 

  Access Paper or Ask Questions

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


Oct 14, 2019
David Stutz, Matthias Hein, Bernt Schiele


  Access Paper or Ask Questions

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


Sep 26, 2019
Alexander Meinke, Matthias Hein


  Access Paper or Ask Questions

Sparse and Imperceivable Adversarial Attacks


Sep 11, 2019
Francesco Croce, Matthias Hein

* Accepted to ICCV 2019 

  Access Paper or Ask Questions

Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack


Jul 03, 2019
Francesco Croce, Matthias Hein


  Access Paper or Ask Questions

Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks


Jun 08, 2019
Maksym Andriushchenko, Matthias Hein


  Access Paper or Ask Questions

Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$


May 27, 2019
Francesco Croce, Matthias Hein


  Access Paper or Ask Questions

Spectral Clustering of Signed Graphs via Matrix Power Means


May 15, 2019
Pedro Mercado, Francesco Tudisco, Matthias Hein

* final version accepted at ICML 2019 

  Access Paper or Ask Questions

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


Mar 27, 2019
Francesco Croce, Jonas Rauber, Matthias Hein


  Access Paper or Ask Questions

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


Dec 13, 2018
Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf


  Access Paper or Ask Questions

Disentangling Adversarial Robustness and Generalization


Dec 03, 2018
David Stutz, Matthias Hein, Bernt Schiele


  Access Paper or Ask Questions

A randomized gradient-free attack on ReLU networks


Nov 28, 2018
Francesco Croce, Matthias Hein

* In GCPR 2018 

  Access Paper or Ask Questions

Logit Pairing Methods Can Fool Gradient-Based Attacks


Oct 29, 2018
Marius Mosbach, Maksym Andriushchenko, Thomas Trost, Matthias Hein, Dietrich Klakow


  Access Paper or Ask Questions

Provable Robustness of ReLU networks via Maximization of Linear Regions


Oct 17, 2018
Francesco Croce, Maksym Andriushchenko, Matthias Hein


  Access Paper or Ask Questions

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


Sep 27, 2018
Quynh Nguyen, Mahesh Chandra Mukkamala, Matthias Hein


  Access Paper or Ask Questions