A Framework for Verification of Wasserstein Adversarial Robustness

no code implementations • 13 Oct 2021 • Tobias Wegel, Felix Assion, David Mickisch, Florens Greßner

Verifying the robustness of classifiers using the Wasserstein metric can be achieved by proving the absence of adversarial examples (certification) or proving their presence (attack).

Adversarial Attack Adversarial Robustness +1

Risk Assessment for Machine Learning Models

no code implementations • 9 Nov 2020 • Paul Schwerdtner, Florens Greßner, Nikhil Kapoor, Felix Assion, René Sass, Wiebke Günther, Fabian Hüger, Peter Schlicht

In this paper we propose a framework for assessing the risk associated with deploying a machine learning model in a specified environment.

BIG-bench Machine Learning

Understanding the Decision Boundary of Deep Neural Networks: An Empirical Study

no code implementations • 5 Feb 2020 • David Mickisch, Felix Assion, Florens Greßner, Wiebke Günther, Mariele Motta

Therefore, we study the minimum distance of data points to the decision boundary and how this margin evolves over the training of a deep neural network.

Autonomous Driving Image Classification

The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks

no code implementations • 17 Jun 2019 • Felix Assion, Peter Schlicht, Florens Greßner, Wiebke Günther, Fabian Hüger, Nico Schmidt, Umair Rasheed

We call this the "attack generator".

Adversarial Attack Adversarial Robustness +4