Close menu

SURE

Sunderland Repository records the research produced by the University of Sunderland including practice-based research and theses.

Consensus Adversarial Defense Method Based on Augmented Examples

Cheng, Yongqiang, Ding, Xintao, Luo, Yonglong, Li, Qingde and Gope, Prosanta (2022) Consensus Adversarial Defense Method Based on Augmented Examples. Transactions on Industrial Informatics. pp. 984-994. ISSN 1941-0050

Item Type: Article

Abstract

Deep learning has been used in many computer-vision-based industrial Internet of Things applications. However, deep neural networks are vulnerable to adversarial examples that have been crafted specifically
to fool a system while being imperceptible to humans. In this article, we propose a consensus defense (Cons-Def) method to defend against adversarial attacks. Cons-Def implements classification and detection based on the consensus of the classifications of the augmented examples,
which are generated based on an individually implemented intensity exchange on the red, green, and blue components of the input image. We train a CNN using augmented examples together with their original examples. For the test image to be assigned to a specific class, the class occurrence of the classifications on its augmented images should be
the maximum and reach a defined threshold. Otherwise, it is detected as an adversarial example. The comparison experiments are implemented on MNIST, CIFAR-10, and ImageNet. The average defense success rate (DSR) against white-box attacks on the test sets of the three datasets
is 80.3%. The average DSR against black-box attacks on CIFAR-10 is 91.4%. The average classification accuracies of Cons-Def on benign examples of the three datasets are 98.0%, 78.3%, and 66.1%. The experimental results show that Cons-Def shows a high classification performance on benign examples and is robust against white-box and black-box adversarial attacks.

[img]
Preview
PDF (Author Accepted Manuscript on Publisher template)
TII3169973-11 - author version.pdf - Accepted Version

Download (5MB) | Preview

More Information

Depositing User: Yongqiang Cheng

Identifiers

Item ID: 16815
Identification Number: https://doi.org/10.1109/TII.2022.3169973
ISSN: 1941-0050
URI: http://sure.sunderland.ac.uk/id/eprint/16815
Official URL: https://ieeexplore.ieee.org/document/9762571

Users with ORCIDS

ORCID for Yongqiang Cheng: ORCID iD orcid.org/0000-0001-7282-7638
ORCID for Xintao Ding: ORCID iD orcid.org/0000-0003-3325-3306
ORCID for Yonglong Luo: ORCID iD orcid.org/0000-0003-4987-0376
ORCID for Qingde Li: ORCID iD orcid.org/0000-0001-5998-7565
ORCID for Prosanta Gope: ORCID iD orcid.org/0000-0003-2786-0273

Catalogue record

Date Deposited: 11 Jan 2024 12:11
Last Modified: 11 Jan 2024 12:11

Contributors

Author: Yongqiang Cheng ORCID iD
Author: Xintao Ding ORCID iD
Author: Yonglong Luo ORCID iD
Author: Qingde Li ORCID iD
Author: Prosanta Gope ORCID iD

University Divisions

Faculty of Technology > School of Computer Science

Subjects

Computing > Cybersecurity
Computing > Data Science
Computing > Artificial Intelligence
Computing

Actions (login required)

View Item (Repository Staff Only) View Item (Repository Staff Only)