Applied Sciences |
您所在的位置：网站首页 › originaldesigner › Applied Sciences |
Applied Sciences
|
Next Article in Journal
Personalized Privacy Protection-Preserving Collaborative Filtering Algorithm for Recommendation Systems
Previous Article in Journal
Human-Focused Digital Twin Applications for Occupational Safety and Health in Workplaces: A Brief Survey and Research Directions
Journals
Active Journals
Find a Journal
Proceedings Series
Topics
Information
For Authors
For Reviewers
For Editors
For Librarians
For Publishers
For Societies
For Conference Organizers
Open Access Policy
Institutional Open Access Program
Special Issues Guidelines
Editorial Process
Research and Publication Ethics
Article Processing Charges
Awards
Testimonials
Author Services
Initiatives
Sciforum
MDPI Books
Preprints.org
Scilit
SciProfiles
Encyclopedia
JAMS
Proceedings Series
About
Overview
Contact
Careers
News
Blog
Sign In / Sign Up
Notice
clear
Notice
You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader. Continue Cancel clearAll articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess. Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications. Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers. Editor鈥檚 Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal. 
Journals
Active Journals
Find a Journal
Proceedings Series
Topics
Information
For Authors
For Reviewers
For Editors
For Librarians
For Publishers
For Societies
For Conference Organizers
Open Access Policy
Institutional Open Access Program
Special Issues Guidelines
Editorial Process
Research and Publication Ethics
Article Processing Charges
Awards
Testimonials
Author Services
Initiatives
Sciforum
MDPI Books
Preprints.org
Scilit
SciProfiles
Encyclopedia
JAMS
Proceedings Series
About
Overview
Contact
Careers
News
Blog
Sign In / Sign Up
Submit
Journals
Applied Sciences
Volume 13
Issue 7
10.3390/app13074599
Submit to this Journal
Review for this Journal
Edit a Special Issue
►
▼
Article Menu
Article Menu
Academic Editors
 Andrea Prati
 Luis Javier Garc铆a Villalba
Vincent A. Cicirello
Subscribe SciFeed
Recommended Articles
Related Info Link
Google Scholar
More by Authors Links
on DOAJ
Ali, S.
Ashraf, S.
Yousaf, M. Sohaib
Riaz, S.
Wang, G.
on Google Scholar
Ali, S.
Ashraf, S.
Yousaf, M. Sohaib
Riaz, S.
Wang, G.
on PubMed
Ali, S.
Ashraf, S.
Yousaf, M. Sohaib
Riaz, S.
Wang, G.
/ajax/scifeed/subscribe
Table of Contents
Altmetric
share
Share
announcement
Help
format_quote
Cite
question_answer
Discuss in SciProfiles
thumb_up
...
Endorse
textsms
...
Comment
Need Help?
Support
Find support for a specific problem in the support section of our website. Get Support FeedbackPlease let us know what you think of our products and services. Give Feedback InformationVisit our dedicated information section to learn more about MDPI. Get Information clear JSmol Viewer clear first_page settings Order Article Reprints Font Type: Arial Georgia Verdana Font Size: Aa Aa Aa Line Spacing: Column Width: Background: This is an early access version, the complete PDF, HTML, and XML versions will be available soon. Open AccessArticle Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks bySaqib Ali 1,2,* , Sana Ashraf 1, Muhammad Sohaib Yousaf 1, Shazia Riaz 1,3 and Guojun Wang 2,*
1
Department of Computer Science, University of Agriculture, Faisalabad 38000, Pakistan
2
School of Computer Science, Guangzhou University, Guangzhou 510006, China
3
Department of Computer Science, Government College Women University, Faisalabad 38000, Pakistan
*
Authors to whom correspondence should be addressed.
Appl. Sci. 2023, 13(7), 4599; https://doi.org/10.3390/app13074599
Received: 12 March 2023
/
Revised: 1 April 2023
/
Accepted: 2 April 2023
/
Published: 5 April 2023
(This article belongs to the Topic Machine and Deep Learning)
Download
Download PDF
Versions Notes
Abstract
The successful outcomes of deep learning (DL) algorithms in diverse fields have prompted researchers to consider backdoor attacks on DL models to defend them in practical applications. Adversarial examples could deceive a safety-critical system, which could lead to hazardous situations. To cope with this, we suggested a segmentation technique that makes hidden trigger backdoor attacks more robust. The tiny trigger patterns are conventionally established by a series of parameters encompassing their DNN size, location, color, shape, and other defining attributes. From the original triggers, alternate triggers are generated to control the backdoor patterns by a third party in addition to their original designer, which can produce a higher success rate than the original triggers. However, the significant downside of these approaches is the lack of automation in the scene segmentation phase, which results in the poor optimization of the threat model. We developed a novel technique that automatically generates alternate triggers to increase the effectiveness of triggers. Image denoising is performed for this purpose, followed by scene segmentation techniques to make the poisoned classifier more robust. The experimental results demonstrated that our proposed technique achieved 99% to 100% accuracy and helped reduce the vulnerabilities of DL models by exposing their loopholes.
Keywords:
backdoor attacks; alternate triggers; data poisoning; adversarial examples; deep learning models
backdoor attacks; alternate triggers; data poisoning; adversarial examples; deep learning models
Share and Cite
MDPI and ACS Style
Ali, S.; Ashraf, S.; Yousaf, M.S.; Riaz, S.; Wang, G. Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks. Appl. Sci. 2023, 13, 4599. https://doi.org/10.3390/app13074599 AMA StyleAli S, Ashraf S, Yousaf MS, Riaz S, Wang G. Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks. Applied Sciences. 2023; 13(7):4599. https://doi.org/10.3390/app13074599 Chicago/Turabian StyleAli, Saqib, Sana Ashraf, Muhammad Sohaib Yousaf, Shazia Riaz, and Guojun Wang. 2023. "Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks" Applied Sciences 13, no. 7: 4599. https://doi.org/10.3390/app13074599 Find Other Styles Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here. Article Metrics No No Article metric data becomes available approximately 24 hours after publication online. Zoom | Orient | As Lines | As Sticks | As Cartoon | As Surface | Previous Scene | Next Scene Cite Export citation file: BibTeX | EndNote | RIS MDPI and ACS StyleAli, S.; Ashraf, S.; Yousaf, M.S.; Riaz, S.; Wang, G. Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks. Appl. Sci. 2023, 13, 4599. https://doi.org/10.3390/app13074599 AMA StyleAli S, Ashraf S, Yousaf MS, Riaz S, Wang G. Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks. Applied Sciences. 2023; 13(7):4599. https://doi.org/10.3390/app13074599 Chicago/Turabian StyleAli, Saqib, Sana Ashraf, Muhammad Sohaib Yousaf, Shazia Riaz, and Guojun Wang. 2023. "Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks" Applied Sciences 13, no. 7: 4599. https://doi.org/10.3390/app13074599 Find Other Styles Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here. clear Appl. Sci., EISSN 2076-3417, Published by MDPI RSS Content Alert Further Information Article Processing Charges Pay an Invoice Open Access Policy Contact MDPI Jobs at MDPI Guidelines For Authors For Reviewers For Editors For Librarians For Publishers For Societies For Conference Organizers MDPI Initiatives Sciforum MDPI Books Preprints.org Scilit SciProfiles Encyclopedia JAMS Proceedings Series Follow MDPI LinkedIn Facebook Twitter
漏 1996-2023 MDPI (Basel, Switzerland) unless otherwise stated
Disclaimer
Disclaimer/Publisher鈥檚 Note: The statements, opinions and data contained in all publications are solely
those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or
the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas,
methods, instructions or products referred to in the content.
Terms and Conditions
Privacy Policy
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.
Accept
We have just recently launched a new version of our website.
Help us to further improve by taking part in this short 5 minute survey
here.
here.
Never show this again
Share Link
Copy
clear
Share
https://www.mdpi.com/2232936
clear
Back to TopTop
|
【本文地址】