While a large amount of work has focused on designing adversarial attack...
While adversarial training has been extensively studied for ResNet
archi...
Adversarial training is widely used to make classifiers robust to a spec...
Sharpness of minima is a promising quantity that can correlate with
gene...
Visual Counterfactual Explanations (VCEs) are an important tool to under...
While adversarial training is generally used as a defense mechanism, rec...
In recent years novel architecture components for image classification h...
Visual counterfactual explanations (VCEs) in image space are an importan...
Adaptive defenses that use test-time optimization promise to improve
rob...
Adversarial training (AT) in order to achieve adversarial robustness wrt...
We show that when taking into account also the image domain [0,1]^d,
est...
Evaluation of adversarial robustness is often error-prone leading to
ove...
A large body of research has focused on adversarial attacks which requir...
The field of defense strategies against adversarial attacks has signific...
We propose the Square Attack, a new score-based black-box l_2 and
l_∞ ad...
Neural networks have been proven to be vulnerable to a variety of advers...
The evaluation of robustness against adversarial manipulation of neural
...
In recent years several adversarial attacks and defenses have been propo...
Modern neural networks are highly non-robust against adversarial
manipul...
It has recently been shown that neural networks but also other classifie...
It has been shown that neural network classifiers are not robust. This r...