Similarity metrics have played a significant role in computer vision to
...
The robustness of image segmentation has been an important research topi...
Neural networks are known to be susceptible to adversarial samples: smal...
Since the control of the Lipschitz constant has a great impact on the
tr...
Important research efforts have focused on the design and training of ne...
Randomized smoothing is the dominant standard for provable defenses agai...
The Lipschitz constant of neural networks has been established as a key
...
Deep neural networks are state-of-the-art in a wide variety of tasks,
ho...
It has been empirically observed that defense mechanisms designed to pro...
This paper tackles the problem of Lipschitz regularization of Convolutio...
Since the discovery of adversarial examples in machine learning, researc...
This paper investigates the theory of robustness against adversarial att...
In this paper, we study deep fully circulant neural networks, that is de...
In real world scenarios, model accuracy is hardly the only factor to
con...