AdversarialQR Revisited: Improving the Adversarial Efficacy

Autor:	Kazunori Kotani, Prarinya Siritanawan, Pongpeera Sukasem, Karin Sumonkayothin, Poomdharm Benjasirimonkol, Aran Chindaudom
Rok vydání:	2020
Předmět:	Adversarial system Contextual image classification Process (engineering) business.industry Computer science Deep learning Code (cryptography) Artificial intelligence Machine learning computer.software_genre business Convolutional neural network computer
Zdroj:	Communications in Computer and Information Science ISBN: 9783030638191 ICONIP (4)
DOI:	10.1007/978-3-030-63820-7_91
Popis:	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.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::08f877baed86fc1362b2080e17670b54 https://doi.org/10.1007/978-3-030-63820-7_91 Zobrazit plný text záznamu