AdverseGen: A Practical Tool for Generating Adversarial Examples to Deep Neural Networks Using Black-Box Approaches

Keyuan ZHANG, Kaiyue WU, Siyu CHEN, Yunce ZHAO, Xin YAO*

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

Abstract

Deep neural networks are fragile as they are easily fooled by inputs with deliberate perturbations, which are key concerns in image security issues. Given a trained neural network, we are always curious about whether the neural network has learned the concept that we’d like it to learn. We want to know whether there might be some vulnerabilities of the neural network that could be exploited by hackers. It could be useful if there is a tool that can be used by non-experts to test a trained neural network and try to find its vulnerabilities. In this paper, we introduce a tool named AdverseGen for generating adversarial examples to a trained deep neural network using the black-box approach, i.e., without using any information about the neural network architecture and its gradient information. Our tool provides customized adversarial attacks for both non-professional users and developers. It can be invoked by a graphical user interface or command line mode to launch adversarial attacks. Moreover, this tool supports different attack goals (targeted, non-targeted) and different distance metrics. © 2021, Springer Nature Switzerland AG.
Original languageEnglish
Title of host publicationArtificial Intelligence XXXVIII : 41st SGAI International Conference on Artificial Intelligence, AI 2021, Cambridge, UK, December 14–16, 2021, Proceedings
EditorsMax BRAMER, Richard ELLIS
PublisherSpringer Science and Business Media Deutschland GmbH
Pages313-326
Number of pages14
ISBN (Electronic)9783030911003
ISBN (Print)9783030910990
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event41st SGAI International Conference on Artificial Intelligence - Cambridge, United Kingdom
Duration: 14 Dec 202116 Dec 2021

Publication series

NameLecture Notes in Artificial Intelligence
PublisherSpringer
Volume13101
ISSN (Print)2945-9133
ISSN (Electronic)2945-9141
NameLecture Notes in Computer Science
PublisherSpringer
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference41st SGAI International Conference on Artificial Intelligence
Abbreviated titleSGAI-AI 2021
Country/TerritoryUnited Kingdom
CityCambridge
Period14/12/2116/12/21

Bibliographical note

This work was supported by the Research Institute of Trustworthy Autonomous Systems, the Guangdong Provincial Key Laboratory (Grant No. 2020B121201001), the Program for Guangdong Introducing Innovative and Enterpreneurial Teams (Grant No. 2017ZT07X386) and Shenzhen Science and Technology Program (Grant No. KQTD2016112514355531).

Keywords

  • Adversarial examples
  • Black-box attack
  • Deep neural networks

Fingerprint

Dive into the research topics of 'AdverseGen: A Practical Tool for Generating Adversarial Examples to Deep Neural Networks Using Black-Box Approaches'. Together they form a unique fingerprint.

Cite this