Bias-based Universal Adversarial Patch Attack for Automatic Check-out

• Main Authors: Liu, Aishan, Wang, Jiakai, Liu, Xianglong, Cao, Bowen, Zhang, Chongzhi, Yu, Hang
• Format: Journal Article
• Language: English
• Published: 19.05.2020
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Computer Science - Learning

Adversarial examples are inputs with imperceptible perturbations that easily misleading deep neural networks(DNNs). Recently, adversarial patch, with noise confined to a small and localized patch, has emerged for its easy feasibility in real-world scenarios. However, existing strategies failed to ge...