One pixel attack for fooling deep neural networks

10/24/2017
by   Jiawei Su, et al.
0

Recent research has revealed that the output of Deep Neural Networks (DNN) can be easily altered by adding relatively small perturbations to the input vector. In this paper, we analyze an attack in an extremely limited scenario where only one pixel can be modified. For that we propose a novel method for generating one-pixel adversarial perturbations based on differential evolution. It requires less adversarial information and can fool more types of networks. The results show that 70.97 one target class by modifying just one pixel with 97.47 Thus, the proposed attack explores a different take on adversarial machine learning in an extreme limited scenario, showing that current DNNs are also vulnerable to such low dimension attacks.

READ FULL TEXT

page 1

page 2

page 7

page 8

research
04/19/2018

Attacking Convolutional Neural Network using Differential Evolution

The output of Convolutional Neural Networks (CNN) has been shown to be d...
research
08/05/2019

A principled approach for generating adversarial images under non-smooth dissimilarity metrics

Deep neural networks are vulnerable to adversarial perturbations: small ...
research
07/15/2021

Adversarial Attack for Uncertainty Estimation: Identifying Critical Regions in Neural Networks

We propose a novel method to capture data points near decision boundary ...
research
11/24/2022

Tracking Dataset IP Use in Deep Neural Networks

Training highly performant deep neural networks (DNNs) typically require...
research
05/31/2018

Sequential Attacks on Agents for Long-Term Adversarial Goals

Reinforcement learning (RL) has advanced greatly in the past few years w...
research
03/01/2017

Detecting Adversarial Samples from Artifacts

Deep neural networks (DNNs) are powerful nonlinear architectures that ar...
research
01/15/2018

Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks

Machine learning systems based on deep neural networks, being able to pr...

Please sign up or login with your details

Forgot password? Click here to reset