DeepAI AI Chat
Log In Sign Up

EdgeFool: An Adversarial Image Enhancement Filter

10/27/2019
by   Ali Shahin Shamsabadi, et al.
30

Adversarial examples are intentionally perturbed images that mislead classifiers. These images can, however, be easily detected using denoising algorithms, when high-frequency spatial perturbations are used, or can be noticed by humans, when perturbations are large. In this paper, we propose EdgeFool, an adversarial image enhancement filter that learns structure-aware adversarial perturbations. EdgeFool generates adversarial images with perturbations that enhance image details via training a fully convolutional neural network end-to-end with a multi-task loss function. This loss function accounts for both image detail enhancement and class misleading objectives. We evaluate EdgeFool on three classifiers (ResNet-50, ResNet-18 and AlexNet) using two datasets (ImageNet and Private-Places365) and compare it with six adversarial methods (DeepFool, SparseFool, Carlini-Wagner, SemanticAdv, Non-targeted and Private Fast Gradient Sign Methods).

READ FULL TEXT

page 1

page 2

page 3

page 4

12/06/2017

Generative Adversarial Perturbations

In this paper, we propose novel generative models for creating adversari...
03/24/2020

Adversarial Perturbations Fool Deepfake Detectors

This work uses adversarial perturbations to enhance deepfake images and ...
08/02/2016

A study of the effect of JPG compression on adversarial images

Neural network image classifiers are known to be vulnerable to adversari...
08/13/2020

Semantically Adversarial Learnable Filters

We present the first adversarial framework that crafts perturbations tha...
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...
02/03/2020

A Differentiable Color Filter for Generating Unrestricted Adversarial Images

We propose Adversarial Color Filtering (AdvCF), an approach that uses a ...
07/04/2017

UPSET and ANGRI : Breaking High Performance Image Classifiers

In this paper, targeted fooling of high performance image classifiers is...

Code Repositories

EdgeFool

PyTorch implementation of EdgeFool: An Adversarial Image Enhancement Filter, ICASSP2020


view repo