Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks

01/15/2018
by   Bo Luo, et al.
0

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to adversarial example attack, which generates malicious output by adding slight perturbations to the input. Previous adversarial example crafting methods, however, use simple metrics to evaluate the distances between the original examples and the adversarial ones, which could be easily detected by human eyes. In addition, these attacks are often not robust due to the inevitable noises and deviation in the physical world. In this work, we present a new adversarial example attack crafting method, which takes the human perceptual system into consideration and maximizes the noise tolerance of the crafted adversarial example. Experimental results demonstrate the efficacy of the proposed technique.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

page 5

12/06/2018

On Configurable Defense against Adversarial Example Attacks

Machine learning systems based on deep neural networks (DNNs) have gaine...
12/05/2019

Region-Wise Attack: On Efficient Generation of Robust Physical Adversarial Examples

Deep neural networks (DNNs) are shown to be susceptible to adversarial e...
03/07/2019

Attack Type Agnostic Perceptual Enhancement of Adversarial Images

Adversarial images are samples that are intentionally modified to deceiv...
10/24/2017

One pixel attack for fooling deep neural networks

Recent research has revealed that the output of Deep Neural Networks (DN...
12/31/2020

Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions

Adversarial examples are input examples that are specifically crafted to...
02/28/2020

Applying Tensor Decomposition to image for Robustness against Adversarial Attack

Nowadays the deep learning technology is growing faster and shows dramat...
11/30/2021

Human Imperceptible Attacks and Applications to Improve Fairness

Modern neural networks are able to perform at least as well as humans in...
This week in AI

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