An imperceptible data augmentation based blackbox clean-label backdoor attack on deep neural networks

• Main Authors: Xu, Chaohui, Liu, Wenye, Zheng, Yue, Wang, Si, Chang, Chip Hong
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2024
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision; Clean-Label Backdoor Attack; Data Augmentation; Data Poisoning; Deep Neural Networks; Edge AI
• Online Access: https://hdl.handle.net/10356/173118
• Institution: Nanyang Technological University

Deep neural networks (DNNs) have permeated into many diverse application domains, making them attractive targets of malicious attacks. DNNs are particularly susceptible to data poisoning attacks. Such attacks can be made more venomous and harder to detect by poisoning the training samples without ch...