Security in defect detection: A new one-pixel attack for fooling DNNs

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60076658%3A12310%2F23%3A43907484" target="_blank" >RIV/60076658:12310/23:43907484 - isvavai.cz</a>

Result on the web

<a href="https://www.sciencedirect.com/science/article/pii/S1319157823002434?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S1319157823002434?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.jksuci.2023.101689" target="_blank" >10.1016/j.jksuci.2023.101689</a>

Result language

angličtina

Original language name

Security in defect detection: A new one-pixel attack for fooling DNNs

Original language description

The Industrial 5.0 Model integrates enabling technologies such as deep learning, digital twins, and the meta-universe with new development concepts. However, model and data security may pose challenges for developing zero-defect production and other industrial manufacturing industries. To address this issue, we generate adversarial examples using a one-pixel attack in adversarial machine learning, which can fool the defect detection classification model. The traditional one-pixel attack based on the Differential Evolution (DE) algorithm has limited global search ability. Therefore, we use a novel algorithm called Teaching and Learning-based Moth-Flame Optimization (TLMFO), which enhances the global search performance and improves the attack effectiveness. We evaluate TLMFO on benchmark functions and attacks on Cifar10 and ImageNet datasets, and compare it with MFO and DE. The results show that TLMFO outperforms both MFO and DE in terms of accuracy and speed of convergence. Moreover, TLMFO achieves notably better attack effectiveness than DE under targeted and untargeted attacks on the Cifar10 dataset and under-targeted attacks on the ImageNet dataset. Our research confirms that safety prevention is a link worth considering in developing Industry 5.0.(c) 2023 The Author(s). Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Journal of King Saud University-Computer and Information Sciences

ISSN

1319-1578

e-ISSN

2213-1248

Volume of the periodical

35

Issue of the periodical within the volume

8

Country of publishing house

NL - THE KINGDOM OF THE NETHERLANDS

Number of pages

16

Pages from-to

—

UT code for WoS article

001080358700001

EID of the result in the Scopus database

2-s2.0-85172465788