ManiGen: A Manifold Aided Black-Box Generator of Adversarial Examples

<p dir="ltr">From recent research work, it has been shown that neural network (NN) classifiers are vulnerable to adversarial examples which contain special perturbations that are ignored by human eyes while can mislead NN classifiers. In this paper, we propose a practical black-box a...

Full description

Saved in:
Bibliographic Details
Main Author: Guanxiong Liu (2104315) (author)
Other Authors: Issa Khalil (16855449) (author), Abdallah Khreishah (16855455) (author), Abdulelah Algosaibi (18973903) (author), Adel Aldalbahi (18973906) (author), Mohammed Alnaeem (18973909) (author), Abdulaziz Alhumam (18973912) (author), Muhammad Anan (18973915) (author)
Published: 2020
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513511408795648
author Guanxiong Liu (2104315)
author2 Issa Khalil (16855449)
Abdallah Khreishah (16855455)
Abdulelah Algosaibi (18973903)
Adel Aldalbahi (18973906)
Mohammed Alnaeem (18973909)
Abdulaziz Alhumam (18973912)
Muhammad Anan (18973915)
author2_role author
author
author
author
author
author
author
author_facet Guanxiong Liu (2104315)
Issa Khalil (16855449)
Abdallah Khreishah (16855455)
Abdulelah Algosaibi (18973903)
Adel Aldalbahi (18973906)
Mohammed Alnaeem (18973909)
Abdulaziz Alhumam (18973912)
Muhammad Anan (18973915)
author_role author
dc.creator.none.fl_str_mv Guanxiong Liu (2104315)
Issa Khalil (16855449)
Abdallah Khreishah (16855455)
Abdulelah Algosaibi (18973903)
Adel Aldalbahi (18973906)
Mohammed Alnaeem (18973909)
Abdulaziz Alhumam (18973912)
Muhammad Anan (18973915)
dc.date.none.fl_str_mv 2020-10-07T09:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2020.3029270
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/ManiGen_A_Manifold_Aided_Black-Box_Generator_of_Adversarial_Examples/26176819
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Cybersecurity and privacy
Data management and data science
Machine learning
Adversarial examples
machine learning
neural network
manifold
Generators
Manifolds
Artificial neural networks
Optimization
Perturbation methods
Search problems
dc.title.none.fl_str_mv ManiGen: A Manifold Aided Black-Box Generator of Adversarial Examples
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">From recent research work, it has been shown that neural network (NN) classifiers are vulnerable to adversarial examples which contain special perturbations that are ignored by human eyes while can mislead NN classifiers. In this paper, we propose a practical black-box adversarial example generator, dubbed ManiGen. ManiGen does not require any knowledge of the inner state of the target classifier. It generates adversarial examples by searching along the manifold, which is a concise representation of input data. Through extensive set of experiments on different datasets, we show that (1) adversarial examples generated by ManiGen can mislead standalone classifiers by being as successful as the state-of-the-art white-box generator, Carlini, and (2) adversarial examples generated by ManiGen can more effectively attack classifiers with state-of-the-art defenses.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2020.3029270" target="_blank">https://dx.doi.org/10.1109/access.2020.3029270</a></p>
eu_rights_str_mv openAccess
id Manara2_022e52cd2c3ab5ccccdfbfa0ee9c0ffa
identifier_str_mv 10.1109/access.2020.3029270
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/26176819
publishDate 2020
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling ManiGen: A Manifold Aided Black-Box Generator of Adversarial ExamplesGuanxiong Liu (2104315)Issa Khalil (16855449)Abdallah Khreishah (16855455)Abdulelah Algosaibi (18973903)Adel Aldalbahi (18973906)Mohammed Alnaeem (18973909)Abdulaziz Alhumam (18973912)Muhammad Anan (18973915)Information and computing sciencesCybersecurity and privacyData management and data scienceMachine learningAdversarial examplesmachine learningneural networkmanifoldGeneratorsManifoldsArtificial neural networksOptimizationPerturbation methodsSearch problems<p dir="ltr">From recent research work, it has been shown that neural network (NN) classifiers are vulnerable to adversarial examples which contain special perturbations that are ignored by human eyes while can mislead NN classifiers. In this paper, we propose a practical black-box adversarial example generator, dubbed ManiGen. ManiGen does not require any knowledge of the inner state of the target classifier. It generates adversarial examples by searching along the manifold, which is a concise representation of input data. Through extensive set of experiments on different datasets, we show that (1) adversarial examples generated by ManiGen can mislead standalone classifiers by being as successful as the state-of-the-art white-box generator, Carlini, and (2) adversarial examples generated by ManiGen can more effectively attack classifiers with state-of-the-art defenses.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2020.3029270" target="_blank">https://dx.doi.org/10.1109/access.2020.3029270</a></p>2020-10-07T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2020.3029270https://figshare.com/articles/journal_contribution/ManiGen_A_Manifold_Aided_Black-Box_Generator_of_Adversarial_Examples/26176819CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/261768192020-10-07T09:00:00Z
spellingShingle ManiGen: A Manifold Aided Black-Box Generator of Adversarial Examples
Guanxiong Liu (2104315)
Information and computing sciences
Cybersecurity and privacy
Data management and data science
Machine learning
Adversarial examples
machine learning
neural network
manifold
Generators
Manifolds
Artificial neural networks
Optimization
Perturbation methods
Search problems
status_str publishedVersion
title ManiGen: A Manifold Aided Black-Box Generator of Adversarial Examples
title_full ManiGen: A Manifold Aided Black-Box Generator of Adversarial Examples
title_fullStr ManiGen: A Manifold Aided Black-Box Generator of Adversarial Examples
title_full_unstemmed ManiGen: A Manifold Aided Black-Box Generator of Adversarial Examples
title_short ManiGen: A Manifold Aided Black-Box Generator of Adversarial Examples
title_sort ManiGen: A Manifold Aided Black-Box Generator of Adversarial Examples
topic Information and computing sciences
Cybersecurity and privacy
Data management and data science
Machine learning
Adversarial examples
machine learning
neural network
manifold
Generators
Manifolds
Artificial neural networks
Optimization
Perturbation methods
Search problems