Imperceptible misclassification attack on deep learning accelerator by glitch injection

• Main Authors: Liu, Wenye, Chang, Chip-Hong, Zhang, Fan, Lou, Xiaoxuan
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2021
• Subjects: Engineering::Electrical and electronic engineering; Machine Learning; Hardware
• Online Access: https://hdl.handle.net/10356/145856
• Institution: Nanyang Technological University

The convergence of edge computing and deep learning empowers endpoint hardwares or edge devices to perform inferences locally with the help of deep neural network (DNN) accelerator. This trend of edge intelligence invites new attack vectors, which are methodologically different from the well-known s...