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
•Posted Content
Dead Pixel Test Using Effective Receptive Field.
TL;DR: In this article, the size of the receptive field of CNNs has been evaluated and it has been shown that the number of pixels contributing to the final output does not accurately represent the classification accuracy.
9
On the Assessment of Robustness of Telemedicine Applications against Adversarial Machine Learning Attacks
Ibrahim Yilmaz,Mohamed Baza,Ramy Amer,Amar A. Rasheed,Fathi Amsaad,Rasha Morsi +5 more
- 26 Jul 2021
TL;DR: In this paper, the impact of adversarial attacks on mammographic image classifier was investigated and the structural similarity index was used to determine similarity between clean images and adversarial images.
9
An Adversarial Attack Based on Incremental Learning Techniques for Unmanned in 6G Scenes
TL;DR: An adversarial attack based on incremental learning techniques for unmanned scenes can retain information previously learned by the model and can renew the old model to learn new model, thereby continually adding small perturbation to legitimate examples.
9
•Posted Content
Perceptual Quality-preserving Black-Box Attack against Deep Learning Image Classifiers
TL;DR: In this article, a black-box attack along a low-distortion path is proposed to improve both the attack efficiency and the perceptual quality of the adversarial image, which can be applied to real-world systems.
9
UxV-based Deep-Learning Integrated Automated and Secure Garbage Management Scheme using Blockchain
15 Apr 2023
TL;DR: Wang et al. as mentioned in this paper presented a DL model integrated automated and secure garbage management scheme using unmanned any vehicle (UxV) to minimize the human effort in terms of the traditional garbage management system.
9
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