AI Chat AI Image Generator AI Video Text to Speech

Inspecting adversarial examples using the Fisher information

09/12/2019

∙

by Jörg Martin, et al.

∙

∙

Adversarial examples are slight perturbations that are designed to fool artificial neural networks when fed as an input. In this work the usability of the Fisher information for the detection of such adversarial attacks is studied. We discuss various quantities whose computation scales well with the network size, study their behavior on adversarial examples and show how they can highlight the importance of single input neurons, thereby providing a visual tool for further analyzing (un-)reasonable behavior of a neural network. The potential of our methods is demonstrated by applications to the MNIST, CIFAR10 and Fruits-360 datasets.

Jörg Martin
5 publications
Clemens Elster
10 publications

page 1

page 2

page 3

page 4

research

∙ 02/19/2018

Robustness of Rotation-Equivariant Networks to Adversarial Perturbations

Deep neural networks have been shown to be vulnerable to adversarial exa...

0 Beranger Dumont, et al. ∙

research

∙ 09/13/2019

Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix

We propose a scheme for defending against adversarial attacks by suppres...

0 Chaomin Shen, et al. ∙

research

∙ 02/15/2021

And/or trade-off in artificial neurons: impact on adversarial robustness

Since its discovery in 2013, the phenomenon of adversarial examples has ...

14 Alessandro Fontana, et al. ∙

research

∙ 01/03/2018

Neural Networks in Adversarial Setting and Ill-Conditioned Weight Space

Recently, Neural networks have seen a huge surge in its adoption due to ...

0 Mayank Singh, et al. ∙

research

∙ 07/04/2020

Relationship between manifold smoothness and adversarial vulnerability in deep learning with local errors

Artificial neural networks can achieve impressive performances, and even...

0 Zijian Jiang, et al. ∙

research

∙ 09/25/2018

Neural Networks with Structural Resistance to Adversarial Attacks

In adversarial attacks to machine-learning classifiers, small perturbati...

0 Luca de Alfaro, et al. ∙

research

∙ 07/23/2020

Scalable Inference of Symbolic Adversarial Examples

We present a novel method for generating symbolic adversarial examples: ...

4 Dimitar I. Dimitrov, et al. ∙