Exploring the Space of Adversarial Images

10/19/2015
by   Pedro Tabacof, et al.
0

Adversarial examples have raised questions regarding the robustness and security of deep neural networks. In this work we formalize the problem of adversarial images given a pretrained classifier, showing that even in the linear case the resulting optimization problem is nonconvex. We generate adversarial images using shallow and deep classifiers on the MNIST and ImageNet datasets. We probe the pixel space of adversarial images using noise of varying intensity and distribution. We bring novel visualizations that showcase the phenomenon and its high variability. We show that adversarial images appear in large regions in the pixel space, but that, for the same task, a shallow classifier seems more robust to adversarial images than a deep convolutional network.

READ FULL TEXT

page 1

page 3

page 5

page 6

research
06/18/2021

Analyzing Adversarial Robustness of Deep Neural Networks in Pixel Space: a Semantic Perspective

The vulnerability of deep neural networks to adversarial examples, which...
research
03/28/2017

Adversarial Transformation Networks: Learning to Generate Adversarial Examples

Multiple different approaches of generating adversarial examples have be...
research
11/27/2019

Can Attention Masks Improve Adversarial Robustness?

Deep Neural Networks (DNNs) are known to be susceptible to adversarial e...
research
02/04/2019

SNN under Attack: are Spiking Deep Belief Networks vulnerable to Adversarial Examples?

Recently, many adversarial examples have emerged for Deep Neural Network...
research
10/27/2019

Spot Evasion Attacks: Adversarial Examples for License Plate Recognition Systems with Convolution Neural Networks

Recent studies have shown convolution neural networks (CNNs) for image r...
research
05/18/2021

Assessing aesthetics of generated abstract images using correlation structure

Can we generate abstract aesthetic images without bias from natural or h...
research
07/03/2019

Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior

We present a novel method for generating robust adversarial image exampl...

Please sign up or login with your details

Forgot password? Click here to reset