Vulnerability analysis on noise-injection based hardware attack on deep neural networks

• Main Authors: Liu, Wenye, Wang, Si, Chang, Chip-Hong
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2020
• Subjects: Engineering::Electrical and electronic engineering; Deep Neural Networks; Hardware Attacks
• Online Access: https://hdl.handle.net/10356/136863
• Institution: Nanyang Technological University

Despite superior accuracy on most vision recognition tasks, deep neural networks are susceptible to adversarial examples. Recent studies show that adding carefully crafted small perturbations on input layer can mislead a classifier into arbitrary categories. However, most adversarial attack algorith...