Journal Article10.1109/TEVC.2019.2890858
One Pixel Attack for Fooling Deep Neural Networks
TL;DR: This paper proposes a novel method for generating one-pixel adversarial perturbations based on differential evolution (DE), which requires less adversarial information (a black-box attack) and can fool more types of networks due to the inherent features of DE.
read more
Abstract: Recent research has revealed that the output of deep neural networks (DNNs) 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 (DE). It requires less adversarial information (a black-box attack) and can fool more types of networks due to the inherent features of DE. The results show that 67.97% of the natural images in Kaggle CIFAR-10 test dataset and 16.04% of the ImageNet (ILSVRC 2012) test images can be perturbed to at least one target class by modifying just one pixel with 74.03% and 22.91% confidence on average. We also show the same vulnerability on the original CIFAR-10 dataset. 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. Besides, we also illustrate an important application of DE (or broadly speaking, evolutionary computation) in the domain of adversarial machine learning: creating tools that can effectively generate low-cost adversarial attacks against neural networks for evaluating robustness.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
On obtaining sparse semantic solutions for inverse problems, control, and neural network training
TL;DR: A novel column space search approach that emphasizes the data over the model, as well as a novel iterative Levenberg-Marquardt algorithm that smoothly converges to a regularized SVD as opposed to the abrupt truncation inherent to PCA are proposed.
5
A novel and universal GAN-based countermeasure to recover adversarial examples to benign examples
TL;DR: A novel and universal countermeasure to recover multiple types of adversarial examples to benign examples before they are fed into the deep neural network is presented and has a more excellent performance than other countermeasures.
5
i-Sample: Augment Domain Adversarial Adaptation Models for WiFi-based HAR
Zhipeng Zhou,Feng Wang,Wei Gong +2 more
- 18 Aug 2023
TL;DR: i-Sample augments domain adversarial adaptation models for WiFi-based HAR by generating intermediate samples, improving performance with limited source domain data.
5
Towards Robust Fine-Grained Recognition by Maximal Separation of Discriminative Features
Krishna Kanth Nakka,Mathieu Salzmann +1 more
- 30 Nov 2020
TL;DR: This article introduced an attention-based regularization mechanism that maximally separates the latent features of discriminative regions of different classes while minimizing the contribution of the non-discriminative region to the final class prediction.
•Posted Content
Enhanced Expressive Power and Fast Training of Neural Networks by Random Projections
TL;DR: It is proved that the number of neurons required for approximating a Lipschitz function with a prescribed precision depends on the sparsity or the dimension of the manifold and weakly on thedimension of the input vector, which provides the expressive power of fully connected neural networks when the input data are sparse vectors or form a low-dimensional smooth manifold.
References
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
Differential Evolution – A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces
Rainer Storn,Kenneth Price +1 more
TL;DR: In this article, a new heuristic approach for minimizing possibly nonlinear and non-differentiable continuous space functions is presented, which requires few control variables, is robust, easy to use, and lends itself very well to parallel computation.
•Dissertation
Learning Multiple Layers of Features from Tiny Images
Alex Krizhevsky
- 01 Jan 2009
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.
•Book
Pattern Recognition and Machine Learning
Christopher M. Bishop
- 17 Aug 2006
TL;DR: Probability Distributions, linear models for Regression, Linear Models for Classification, Neural Networks, Graphical Models, Mixture Models and EM, Sampling Methods, Continuous Latent Variables, Sequential Data are studied.
Visualizing and Understanding Convolutional Networks
Matthew D. Zeiler,Rob Fergus +1 more
- 06 Sep 2014
TL;DR: A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark.
16.6K
Related Papers (5)
Nicholas Carlini,David Wagner +1 more
- 22 May 2017
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016