Extended Spatially Localized Perturbation GAN (eSLP-GAN) for Robust Adversarial Camouflage Patches

Deep neural networks (DNNs), especially those used in computer vision, are highly vulnerable to adversarial attacks, such as adversarial perturbations and adversarial patches. Adversarial patches, often considered more appropriate for a real-world attack, are attached to the target object or its sur...

Full description

Bibliographic Details

Published in:	Sensors
Main Authors:	Yongsu Kim, Hyoeun Kang, Naufal Suryanto, Harashta Tatimma Larasati, Afifatul Mukaroh, Howon Kim
Format:	Article
Language:	English
Published:	MDPI AG 2021-08-01
Subjects:	adversarial patch generative adversarial networks camouflage
Online Access:	https://www.mdpi.com/1424-8220/21/16/5323