Inspecting adversarial examples using the Fisher information
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.
Code (2)
Similar Papers 제목 키워드 기반
Adversarial Fisher Vectors for Unsupervised Representation Learning
We examine Generative Adversarial Networks (GANs) through the lens of deep Energy Based Models (EBMs), with the goal of exploiting the density model that follows from this formulation. In contrast to a traditional view w…
General ClassificationRepresentation LearningDefending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix
We propose a scheme for defending against adversarial attacks by suppressing the largest eigenvalue of the Fisher information matrix (FIM). Our starting point is one explanation on the rationale of adversarial examples. …
Adversarial DefenseTraffic Sign RecognitionSubspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals
Deep neural networks (DNNs) are notoriously vulnerable to adversarial attacks that place carefully crafted perturbations on normal examples to fool DNNs. To better understand such attacks, a characterization of the featu…
Adversarial DefenseThe Adversarial Attack and Detection under the Fisher Information Metric
Many deep learning models are vulnerable to the adversarial attack, i.e., imperceptible but intentionally-designed perturbations to the input can cause incorrect output of the networks. In this paper, using information g…
Adversarial AttackDetection based Defense against Adversarial Examples from the Steganalysis Point of View
Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible perturbations while dramatically mislead…
Steganalysis