Skip to main navigation Skip to search Skip to main content

Deep Learning Network Model Studies for Adversarial Attack Resistance

  • Fei Chen
  • , Jaeho Choi*
  • *Corresponding author for this work
  • CAIIT

Research output: Contribution to conferenceConference paperpeer-review

Abstract

In the last decades, deep learning neural networks have taken several steps toward higher pattern recognition accuracies. Face recognition is one of the popular topics that have drawn much attention and it is now frequently used in everyday lives. However, the recognition performance suffers easily by irregularities and disturbances. The focus of this work is to explore the security performance of deep learning neural networks by using an adversarial attack approach. The ResNets is the framework of the proposed system and its recognition behaviors under the adversarial attacks are investigated. The experiments are performed by using MNIST and CIFAR-10 datasets and the detection and recognition errors are evaluated. The results show that the proposed systems can be an alternative that can resist perturbations better than the conventional models.

Original languageEnglish
Title of host publicationIntelligent and Fuzzy Techniques for Emerging Conditions and Digital Transformation - Proceedings of the INFUS 2021 Conference
EditorsCengiz Kahraman, Selcuk Cebi, Sezi Cevik Onar, Basar Oztaysi, A. Cagri Tolga, Irem Ucal Sari
PublisherSpringer Science and Business Media Deutschland GmbH
Pages163-169
Number of pages7
ISBN (Print)9783030855765
DOIs
StatePublished - 2022
EventInternational Conference on Intelligent and Fuzzy Systems, INFUS 2021 - Istanbul, Turkey
Duration: 2021.08.242021.08.26

Publication series

NameLecture Notes in Networks and Systems
Volume308
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

ConferenceInternational Conference on Intelligent and Fuzzy Systems, INFUS 2021
Country/TerritoryTurkey
CityIstanbul
Period21.08.2421.08.26

Keywords

  • Adversarial attacks
  • Deep learning neural networks
  • ResNet

Fingerprint

Dive into the research topics of 'Deep Learning Network Model Studies for Adversarial Attack Resistance'. Together they form a unique fingerprint.

Cite this