Perceptually Constrained Adversarial Attacks

02/14/2021
by   Muhammad Zaid Hameed, et al.
0

Motivated by previous observations that the usually applied L_p norms (p=1,2,∞) do not capture the perceptual quality of adversarial examples in image classification, we propose to replace these norms with the structural similarity index (SSIM) measure, which was developed originally to measure the perceptual similarity of images. Through extensive experiments with adversarially trained classifiers for MNIST and CIFAR-10, we demonstrate that our SSIM-constrained adversarial attacks can break state-of-the-art adversarially trained classifiers and achieve similar or larger success rate than the elastic net attack, while consistently providing adversarial images of better perceptual quality. Utilizing SSIM to automatically identify and disallow adversarial images of low quality, we evaluate the performance of several defense schemes in a perceptually much more meaningful way than was done previously in the literature.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 2

page 7

page 8

page 14

page 15

page 16

page 17

06/01/2019

Perceptual Evaluation of Adversarial Attacks for CNN-based Image Classification

Deep neural networks (DNNs) have recently achieved state-of-the-art perf...
02/27/2018

On the Suitability of L_p-norms for Creating and Preventing Adversarial Examples

Much research effort has been devoted to better understanding adversaria...
03/07/2019

Attack Type Agnostic Perceptual Enhancement of Adversarial Images

Adversarial images are samples that are intentionally modified to deceiv...
05/31/2018

Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization

Adversarial attacks involve adding, small, often imperceptible, perturba...
01/31/2021

Towards Imperceptible Query-limited Adversarial Attacks with Perceptual Feature Fidelity Loss

Recently, there has been a large amount of work towards fooling deep-lea...
05/30/2019

Identifying Classes Susceptible to Adversarial Attacks

Despite numerous attempts to defend deep learning based image classifier...
12/01/2016

Adversarial Images for Variational Autoencoders

We investigate adversarial attacks for autoencoders. We propose a proced...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.