Publication: AdversarialQR Revisited: Improving the Adversarial Efficacy
Issued Date
2020-01-01
Resource Type
ISSN
18650937
18650929
18650929
Other identifier(s)
2-s2.0-85097267586
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
Communications in Computer and Information Science. Vol.1332, (2020), 799-806
Suggested Citation
Aran Chindaudom, Pongpeera Sukasem, Poomdharm Benjasirimonkol, Karin Sumonkayothin, Prarinya Siritanawan, Kazunori Kotani AdversarialQR Revisited: Improving the Adversarial Efficacy. Communications in Computer and Information Science. Vol.1332, (2020), 799-806. doi:10.1007/978-3-030-63820-7_91 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/60447
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
AdversarialQR Revisited: Improving the Adversarial Efficacy
Other Contributor(s)
Abstract
© 2020, Springer Nature Switzerland AG. At present, deep learning and convolutional neural networks are currently two of the fastest rising trends as the tool to perform a multitude of tasks such as image classification and computer vision. However, vulnerabilities in such networks can be exploited through input modification, leading to negative consequences to its users. This research aims to demonstrate an adversarial attack method that can hide its attack from human intuition in the form of a QR code, an entity that is most likely to conceal the attack from human acknowledgment due to its widespread use at the current time. A methodology was developed to demonstrate the QR-embedded adversarial patch creation process and attack existing CNN image classification models. Experiments were also performed to investigate trade-offs in different patch shapes and find the patch’s optimal color adjustment to improve scannability while retaining acceptable adversarial efficacy.