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

Add to Chrome

Add to Firefox

Picture for Kathrin Grosse

Kathrin Grosse

Adversarial Vulnerability Bounds for Gaussian Process Classification

Sep 19, 2019
Michael Thomas Smith, Kathrin Grosse, Michael Backes, Mauricio A Alvarez

Figure 1 for Adversarial Vulnerability Bounds for Gaussian Process Classification

Figure 2 for Adversarial Vulnerability Bounds for Gaussian Process Classification

Figure 3 for Adversarial Vulnerability Bounds for Gaussian Process Classification

Figure 4 for Adversarial Vulnerability Bounds for Gaussian Process Classification

* 10 pages + 2 pages references + 7 pages of supplementary. 12 figures. Submitted to AAAI

Access Paper or Ask Questions

Adversarial Initialization -- when your network performs the way I want

Feb 08, 2019
Kathrin Grosse, Thomas A. Trost, Marius Mosbach, Michael Backes, Dietrich Klakow

Figure 1 for Adversarial Initialization -- when your network performs the way I want

Figure 2 for Adversarial Initialization -- when your network performs the way I want

Figure 3 for Adversarial Initialization -- when your network performs the way I want

Figure 4 for Adversarial Initialization -- when your network performs the way I want

* 16 pages, 20 figures

Access Paper or Ask Questions

The Limitations of Model Uncertainty in Adversarial Settings

Dec 06, 2018
Kathrin Grosse, David Pfaff, Michael T. Smith, Michael Backes

Figure 1 for The Limitations of Model Uncertainty in Adversarial Settings

Figure 2 for The Limitations of Model Uncertainty in Adversarial Settings

Figure 3 for The Limitations of Model Uncertainty in Adversarial Settings

Figure 4 for The Limitations of Model Uncertainty in Adversarial Settings

* 14 pages, 9 figures, 2 tables

Access Paper or Ask Questions

Killing Three Birds with one Gaussian Process: Analyzing Attack Vectors on Classification

Jun 06, 2018
Kathrin Grosse, Michael T. Smith, Michael Backes

Figure 1 for Killing Three Birds with one Gaussian Process: Analyzing Attack Vectors on Classification

Figure 2 for Killing Three Birds with one Gaussian Process: Analyzing Attack Vectors on Classification

Figure 3 for Killing Three Birds with one Gaussian Process: Analyzing Attack Vectors on Classification

Figure 4 for Killing Three Birds with one Gaussian Process: Analyzing Attack Vectors on Classification

* 15 pages, 5 tables, 12 figures

Access Paper or Ask Questions

How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models

Feb 16, 2018
Kathrin Grosse, David Pfaff, Michael Thomas Smith, Michael Backes

Figure 1 for How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models

Figure 2 for How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models

Figure 3 for How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models

Figure 4 for How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models

* 8 pages, 7 pages appendix, 8 figures and 13 tables; improved writing and figures

Access Paper or Ask Questions

On the (Statistical) Detection of Adversarial Examples

Oct 17, 2017
Kathrin Grosse, Praveen Manoharan, Nicolas Papernot, Michael Backes, Patrick McDaniel

Figure 1 for On the (Statistical) Detection of Adversarial Examples

Figure 2 for On the (Statistical) Detection of Adversarial Examples

Figure 3 for On the (Statistical) Detection of Adversarial Examples

Figure 4 for On the (Statistical) Detection of Adversarial Examples

* 13 pages, 4 figures, 5 tables. New version: improved writing, incorporating external feedback

Access Paper or Ask Questions

Adversarial Perturbations Against Deep Neural Networks for Malware Classification

Jun 16, 2016
Kathrin Grosse, Nicolas Papernot, Praveen Manoharan, Michael Backes, Patrick McDaniel

Figure 1 for Adversarial Perturbations Against Deep Neural Networks for Malware Classification

Figure 2 for Adversarial Perturbations Against Deep Neural Networks for Malware Classification

Figure 3 for Adversarial Perturbations Against Deep Neural Networks for Malware Classification

Figure 4 for Adversarial Perturbations Against Deep Neural Networks for Malware Classification

* version update: correcting typos, incorporating external feedback

Access Paper or Ask Questions