1 code implementation • 28 Feb 2022 • Francesco Croce, Sven Gowal, Thomas Brunner, Evan Shelhamer, Matthias Hein, Taylan Cemgil
Adaptive defenses, which optimize at test time, promise to improve adversarial robustness.
1 code implementation • 14 Jun 2019 • Thomas Brunner, Frederik Diehl, Alois Knoll
Many optimization methods for generating black-box adversarial examples have been proposed, but the aspect of initializing said optimizers has not been considered in much detail.
no code implementations • 19 May 2019 • Thomas Brunner, Frederik Diehl, Michael Truong Le, Alois Knoll
Semantic Embeddings are a popular way to represent knowledge in the field of zero-shot learning.
1 code implementation • 9 Apr 2019 • Chih-Hong Cheng, Chung-Hao Huang, Thomas Brunner, Vahid Hashemi
We study the problem of safety verification of direct perception neural networks, where camera images are used as inputs to produce high-level features for autonomous vehicles to make control decisions.
no code implementations • 4 Mar 2019 • Frederik Diehl, Thomas Brunner, Michael Truong Le, Alois Knoll
We show that prediction error in scenarios with much interaction decreases by 30% compared to a model that does not take interactions into account.
3 code implementations • ICCV 2019 • Thomas Brunner, Frederik Diehl, Michael Truong Le, Alois Knoll
We consider adversarial examples for image classification in the black-box decision-based setting.