Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Mobile Networks and Applications
Published in: Mobile Networks and Applications 4/2021

20-01-2020

An Evolutionary-Based Black-Box Attack to Deep Neural Network Classifiers

Authors: Yutian Zhou, Yu-an Tan, Quanxin Zhang, Xiaohui Kuang, Yahong Han, Jingjing Hu

Published in: Mobile Networks and Applications | Issue 4/2021

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Deep neural networks are susceptible to tiny crafted adversarial perturbations which are always added to all the pixels of the image to craft an adversarial example. Most of the existing adversarial attacks can reduce the L2 distance between the adversarial image and the source image to a minimum but ignore the L0 distance which is still huge. To address this issue, we introduce a new black-box adversarial attack based on evolutionary method and bisection method, which can greatly reduce the L0 distance while limiting the L2 distance. By flipping pixels of the target image, an adversarial example is generated, in which a small number of pixels come from the target image and the rest pixels are from the source image. Experiments show that our attack method is able to generate high quality adversarial examples steadily. Especially for generating adversarial examples for large scale images, our method performs better.
previous article Cryptanalysis of a Public Key Cryptosystem Based on Data Complexity under Quantum Environment
next article Network Risk Assessment Based on Baum Welch Algorithm and HMM

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
Show more products
Footnotes
Literature
1.
Collobert R, Weston J (2008) A unified architecture for natural language processing: deep neural networks with multitask learning[C]//proceedings of the 25th international conference on machine learning. ACM:160–167
2.
Hinton G, Deng L, Yu D et al (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups[J]. IEEE Signal Process Mag 29(6):82–97CrossRef
3.
Krizhevsky A , Sutskever I , Hinton G . ImageNet Classification with Deep Convolutional Neural Networks[J]. Adv Neural Inf Proces Syst, 2012, 25(2)
4.
Chen HH, Chen M, Chiu CC (2016) The integration of artificial neural networks and text mining to forecast gold futures prices[J]. Communications in Statistics - Simulation and Computation 45(4):13MathSciNetCrossRef
5.
Yerima SY, Sezer S (2018) DroidFusion: a novel multilevel classifier fusion approach for android malware detection[J]. IEEE Transactions on Cybernetics:1–14
6.
He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770–778
7.
Carlini N, Wagner D. Adversarial examples are not easily detected: bypassing ten detection methods[J]. 2017CrossRef
8.
Nguyen A, Yosinski J, Clune J. Deep neural networks are easily fooled: high confidence predictions for unrecognizable images[J]. 2015
9.
Athalye A , Carlini N , Wagner D . Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples[J]. 2018
10.
Huang S, Papernot N, Goodfellow I, et al. Adversarial attacks on neural network policies[J]. arXiv preprint arXiv:1702.02284, 2017
11.
Brendel W, Rauber J, Bethge M. Decision-based adversarial attacks: reliable attacks against black-box machine learning models[J]. 2018
12.
Barreno M, Nelson B, Sears R et al (2006) Can machine learning be secure?[C]//proceedings of the 2006 ACM symposium on information, computer and communications security. ACM:16–25
13.
14.
Szegedy C, Zaremba W, Sutskever I, et al. Intriguing properties of neural networks[J]. arXiv preprint arXiv:1312.6199, 2013
15.
16.
Kurakin A, Goodfellow I, Bengio S. Adversarial examples in the physical world[J]. arXiv preprint arXiv:1607.02533, 2016
17.
Papernot N, McDaniel P, Jha S et al (2016) The limitations of deep learning in adversarial settings[C]//security and privacy (EuroS&P), 2016 IEEE European symposium on. IEEE:372–387
18.
Su J, Vargas D V, Kouichi S. One pixel attack for fooling deep neural networks[J]. arXiv preprint arXiv:1710.08864, 2017
19.
Papernot N, Mcdaniel P, Xi W, et al. Distillation as a defense to adversarial perturbations against deep neural networks[C]// Security & Privacy. 2016
20.
Carlini N, Wagner D (2017) Towards evaluating the robustness of neural networks[C]//2017 IEEE symposium on security and privacy (SP). IEEE:39–57
21.
Moosavidezfooli SM, Fawzi A, Frossard P (2016) DeepFool: a simple and accurate method to fool deep neural networks[C]// computer vision and pattern recognition. IEEE:2574–2582
22.
Papernot N, Mcdaniel P, Goodfellow I, et al. Practical black-box attacks against deep learning systems using adversarial examples[J]. 2016
23.
Andor D, Alberti C, Weiss D, et al. Globally normalized transition-based neural networks[J]. arXiv preprint arXiv:1603.06042, 2016
24.
Liu Y, Chen X, Liu C, et al. Delving into transferable adversarial examples and black-box attacks[J]. arXiv preprint arXiv:1611.02770, 2016
25.
Tramèr F, Papernot N, Goodfellow I, et al. The space of transferable adversarial examples[J]. arXiv preprint arXiv:1704.03453, 2017
26.
Narodytska N, Kasiviswanathan S P. Simple black-box adversarial perturbations for deep networks[J]. 2016
27.
Jin Y (2005) Jürgen Branke. Evolutionary optimization in uncertain environments---a survey[J]. IEEE Trans Evol Comput 9(3):303–317CrossRef
28.
LeCun Y. The MNIST database of handwritten digits[J]. http://​yann.​ lecun. com/exdb/mnist/, 1998
29.
Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database[C]// IEEE conference on Computer Vision & Pattern Recognition. 2009
Metadata
Title
An Evolutionary-Based Black-Box Attack to Deep Neural Network Classifiers
Authors
Yutian Zhou
Yu-an Tan
Quanxin Zhang
Xiaohui Kuang
Yahong Han
Jingjing Hu
Publication date
20-01-2020
Publisher
Springer US
Published in
Mobile Networks and Applications / Issue 4/2021
Print ISSN: 1383-469X
Electronic ISSN: 1572-8153
DOI
https://doi.org/10.1007/s11036-019-01499-x

Other articles of this Issue 4/2021

Mobile Networks and Applications 4/2021 Go to the issue

OriginalPaper

Network Risk Assessment Based on Baum Welch Algorithm and HMM

OriginalPaper

An Efficient Bounded Model Checking Approach for Web Service Composition

OriginalPaper

Malware Detection Based on Multi-level and Dynamic Multi-feature Using Ensemble Learning at Hypervisor

OriginalPaper

Security Assessment for Interdependent Heterogeneous Cyber Physical Systems

OriginalPaper

Secure Encrypted Data Deduplication Based on Data Popularity

OriginalPaper

A Timestamp-Regulating VoLTE Covert Channel against Statistical Analysis