activity
20202022
most citedExploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks

9 citations · 13 across the 3 of their papers we have counts for

collaborators

5 papers

cs.LG20222 cited

Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification

Leo Schwinn, Leon Bungert, An Nguyen +5

The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to e…

cs.LG20219 cited

Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks

Leo Schwinn, René Raab, An Nguyen +2

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluat…

cs.LG20212 cited

Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis

Leo Schwinn, An Nguyen, René Raab +5

The susceptibility of deep neural networks to untrustworthy predictions, including out-of-distribution (OOD) data and adversarial examples, still prevent their widespread use in sa…

cs.LG2020

Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks

Leo Schwinn, An Nguyen, René Raab +4

The vulnerability of deep neural networks to small and even imperceptible perturbations has become a central topic in deep learning research. Although several sophisticated defense…

cs.LG2020

Towards Rapid and Robust Adversarial Training with One-Step Attacks

Leo Schwinn, René Raab, Björn Eskofier

Adversarial training is the most successful empirical method for increasing the robustness of neural networks against adversarial attacks. However, the most effective approaches, l…