Towards verifying the geometric robustness of large-scale neural networks
Deep neural networks (DNNs) are known to be vulnerable to adversarial geometric
transformation. This paper aims to verify the robustness of large-scale DNNs against the …
transformation. This paper aims to verify the robustness of large-scale DNNs against the …
Geometric robustness of deep networks: analysis and improvement
C Kanbak, SM Moosavi-Dezfooli… - Proceedings of the …, 2018 - openaccess.thecvf.com
Deep convolutional neural networks have been shown to be vulnerable to arbitrary
geometric transformations. However, there is no systematic method to measure the …
geometric transformations. However, there is no systematic method to measure the …
The robustness of deep networks: A geometrical perspective
A Fawzi, SM Moosavi-Dezfooli… - IEEE Signal Processing …, 2017 - ieeexplore.ieee.org
Deep neural networks have recently shown impressive classification performance on a
diverse set of visual tasks. When deployed in real-world (noise-prone) environments, it is …
diverse set of visual tasks. When deployed in real-world (noise-prone) environments, it is …
Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks
S Kamath, A Deshpande… - Advances in …, 2021 - proceedings.neurips.cc
Abstract (Non-) robustness of neural networks to small, adversarial pixel-wise perturbations,
and as more recently shown, to even random spatial transformations (eg, translations …
and as more recently shown, to even random spatial transformations (eg, translations …
On the Minimal Adversarial Perturbation for Deep Neural Networks With Provable Estimation Error
Although Deep Neural Networks (DNNs) have shown incredible performance in perceptive
and control tasks, several trustworthy issues are still open. One of the most discussed topics …
and control tasks, several trustworthy issues are still open. One of the most discussed topics …
Provably robust adversarial examples
We introduce the concept of provably robust adversarial examples for deep neural networks-
connected input regions constructed from standard adversarial examples which are …
connected input regions constructed from standard adversarial examples which are …
Rethinking data augmentation for adversarial robustness
Recent work has proposed novel data augmentation methods to improve the adversarial
robustness of deep neural networks. In this paper, we re-evaluate such methods through the …
robustness of deep neural networks. In this paper, we re-evaluate such methods through the …
Provable defense against geometric transformations
Geometric image transformations that arise in the real world, such as scaling and rotation,
have been shown to easily deceive deep neural networks (DNNs). Hence, training DNNs to …
have been shown to easily deceive deep neural networks (DNNs). Hence, training DNNs to …
Efficient neural network robustness certification with general activation functions
Finding minimum distortion of adversarial examples and thus certifying robustness in neural
networks classifiers is known to be a challenging problem. Nevertheless, recently it has …
networks classifiers is known to be a challenging problem. Nevertheless, recently it has …
Using non-invertible data transformations to build adversarial-robust neural networks
Deep neural networks have proven to be quite effective in a wide variety of machine
learning tasks, ranging from improved speech recognition systems to advancing the …
learning tasks, ranging from improved speech recognition systems to advancing the …