Publications

Modeling patterns of smartphone usage and their relationship to cognitive health

Machine Learning for Health Workshop, 33rd Conference on Neural Information Processing Systems, 2019

Jonas Rauber, Emily Fox, Leon Gatys

@inproceedings{rauber2019modeling,
  title={Modeling patterns of smartphone usage and their relationship to cognitive health},
  author={Jonas Rauber and Emily Fox and Leon Gatys},
  booktitle={Machine Learning for Health Workshop, 33rd Conference on Neural Information Processing Systems},
  year={2019},
}

arXiv Workshop


Accurate, reliable and fast robustness evaluation

To appear in Advances in Neural Information Processing Systems 32, 2019

Wieland Brendel, Jonas Rauber, Matthias Kümmerer, Ivan Ustyuzhaninov, Matthias Bethge

@inproceedings{brendel2019accurate,
  title={Accurate, reliable and fast robustness evaluation},
  author={Wieland Brendel and Jonas Rauber and Matthias K{\"u}mmerer and Ivan Ustyuzhaninov and Matthias Bethge},
  booktitle={Advances in Neural Information Processing Systems 32},
  year={2019},
}

arXiv


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

International Journal of Computer Vision

Francesco Croce*, Jonas Rauber*, Matthias Hein

@article{croce2019scaling,
  author="Croce, Francesco
  and Rauber, Jonas
  and Hein, Matthias",
  title="Scaling up the Randomized Gradient-Free Adversarial Attack Reveals Overestimation of Robustness Using Established Attacks",
  journal="International Journal of Computer Vision",
  year="2019",
  month="Oct",
  day="03",
  issn="1573-1405",
  doi="10.1007/s11263-019-01213-0",
  url="https://doi.org/10.1007/s11263-019-01213-0"
}

arXiv Code Springer Link PDF


On Evaluating Adversarial Robustness

arXiv preprint 1902.06705, 2019

Nicholas Carlini, Anish Athalye, Nicolas Papernot, Wieland Brendel, Jonas Rauber, Dimitris Tsipras, Ian Goodfellow, Aleksander Madry, Alexey Kurakin

@article{carlini2019evaluating,
  title={On Evaluating Adversarial Robustness},
  author={Nicholas Carlini and Anish Athalye and Nicolas Papernot and Wieland Brendel and Jonas Rauber and Dimitris Tsipras and Ian Goodfellow and Aleksander Madry and Alexey Kurakin},
  journal={arXiv preprint arXiv:1902.06705},
  year={2019},
}

arXiv Code


Towards the first adversarially robust neural network model on MNIST

International Conference on Learning Representations, 2019

Lukas Schott*, Jonas Rauber*, Matthias Bethge, Wieland Brendel

@inproceedings{schott2018towards,
  title={Towards the first adversarially robust neural network model on {MNIST}},
  author={Lukas Schott and Jonas Rauber and Matthias Bethge and Wieland Brendel},
  booktitle={International Conference on Learning Representations},
  year={2019},
  url={https://openreview.net/forum?id=S1EHOsC9tX},
}

arXiv OpenReview


Generalisation in humans and deep neural networks

Advances in Neural Information Processing Systems 31, 2018

Robert Geirhos*, Carlos R. Medina Temme*, Jonas Rauber*, Heiko H. Schuett, Matthias Bethge, Felix A. Wichmann

@incollection{geirhos2018generalisation,
  title={Generalisation in humans and deep neural networks},
  author={Geirhos, Robert and Temme, Carlos R Medina and Rauber, Jonas and Schuett, Heiko H and Bethge, Matthias and Wichmann, Felix A},
  booktitle={Advances in Neural Information Processing Systems 31},
  year={2018},
}

arXiv Code


Adversarial Vision Challenge

Competition Track of the 32nd Conference on Neural Information Processing Systems, 2018

Wieland Brendel, Jonas Rauber, Alexey Kurakin, Nicolas Papernot, Behar Veliqi, Marcel Salathé, Sharada P. Mohanty, Matthias Bethge

@article{brendel2018adversarial,
  title={Adversarial Vision Challenge},
  author={Brendel, Wieland and Rauber, Jonas and Kurakin, Alexey and Papernot, Nicolas and Veliqi, Behar and Salath{\'e}, Marcel and Mohanty, Sharada P and Bethge, Matthias},
  journal={arXiv preprint arXiv:1808.01976},
  year={2018}
}

arXiv Competition Track crowdAI


Technical Report on the CleverHans v2.1.0 Adversarial Examples Library

arXiv preprint 1610.00768, 2018

Nicolas Papernot, Fartash Faghri, Nicholas Carlini, Ian Goodfellow, Reuben Feinman, Alexey Kurakin, Cihang Xie, Yash Sharma, Tom Brown, Aurko Roy, Alexander Matyasko, Vahid Behzadan, Karen Hambardzumyan, Zhishuai Zhang, Yi-Lin Juang, Zhi Li, Ryan Sheatsley, Abhibhav Garg, Jonathan Uesato, Willi Gierke, Yinpeng Dong, David Berthelot, Paul Hendricks, Jonas Rauber, Rujun Long, Patrick McDaniel

@techreport{papernot2016technical,
  title={Technical report on the cleverhans {v2.1.0} adversarial examples library},
  author={Nicolas Papernot, Fartash Faghri, Nicholas Carlini, Ian Goodfellow, Reuben Feinman, Alexey Kurakin, Cihang Xie, Yash Sharma, Tom Brown, Aurko Roy, Alexander Matyasko, Vahid Behzadan, Karen Hambardzumyan, Zhishuai Zhang, Yi-Lin Juang, Zhi Li, Ryan Sheatsley, Abhibhav Garg, Jonathan Uesato, Willi Gierke, Yinpeng Dong, David Berthelot, Paul Hendricks, Jonas Rauber, Rujun Long, Patrick McDaniel},
  year={2018},
  url={https://arxiv.org/abs/1610.00768},
}

arXiv Code


Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models

International Conference on Learning Representations, 2018

Wieland Brendel*, Jonas Rauber*, Matthias Bethge

@inproceedings{brendel2018decisionbased,
  title={Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models},
  author={Wieland Brendel and Jonas Rauber and Matthias Bethge},
  booktitle={International Conference on Learning Representations},
  year={2018},
  url={https://openreview.net/forum?id=SyZI0GWCZ},
}

arXiv OpenReview Code


Foolbox: A Python toolbox to benchmark the robustness of machine learning models

Reliable Machine Learning in the Wild Workshop, 34th International Conference on Machine Learning, 2017

Jonas Rauber*, Wieland Brendel*, Matthias Bethge

@inproceedings{rauber2017foolbox,
  title={Foolbox: A Python toolbox to benchmark the robustness of machine learning models},
  author={Rauber, Jonas and Brendel, Wieland and Bethge, Matthias},
  booktitle={Reliable Machine Learning in the Wild Workshop, 34th International Conference on Machine Learning},
  year={2017},
  url={http://arxiv.org/abs/1707.04131},
}

arXiv Workshop Code

2019

Autumn School on Deep Learning and Inverse Problems

Bremen, Germany

I will teach a course on How to evaluate adversarial robustness at the Autumn School on Deep Learning and Inverse Problems at the University of Bremen.


Apple

Seattle, USA

Starting end of May, I will be joining Apple's machine learning group in Seattle to do a four-month internship.


ICLR

New Orleans, USA

I will be attending this years International Conference on Learning Representations in New Orleans.


InterFaces

Potsdam, Germany

April 2019


Bosch Research Foundation Meeting

Stuttgart, Germany

Februar 2019

2018

NeurIPS

Montreal, Canada

Thirty-Second Conference on Neural Information Processing Systems, December 2018


DIN Spec Meeting

Berlin, Germany

October 2018


Intel NIS Workshop

Munich, Germany

September 2018


IMPRS-IS Bootcamp

Germany

Yearly meeting of the International Max Planck Research School, July 2018


Stuttgart Media University

Stuttgart, Germany

Workshop to prepare the launch of the Bundeswettbewerb für Künstliche Intelligenz, July 2018


ICLR

Vancouver, Germany

International Conference on Learning Representations, April 2018


Bosch Research Foundation Meeting

Stuttgart, Germany

Februar 2018

2017

IMPRS-IS Bootcamp

Baden-Württemberg, Germany

Yearly meeting of the International Max Planck Research School, October 2017


Bernstein Conference

Göttingen, Germany

September 2017


ICML

Sydney, Australia

International Conference on Machine Learning, August 2017


ETH Learning Systems Summer School

Zurich, Switzerland

July 2017

2016

Started my PhD in Machine Learning

Tübingen, Germany

In November 2016, I started my PhD in the Bethge lab at University of Tübingen and the International Max Planck Research School for Intelligent Systems.


Bernstein Conference

Berlin, Germany

September 2016


MSc in Neural Information Processing

Tübingen, Germany

In July 2016, I graduated from the University of Tübingen as a Master of Science in Neural Information Processing.