Mercury: an automated remote side-channel attack to Nvidia deep learning accelerator

• Main Authors: Yan, Xiaobei, Lou, Xiaoxuan, Xu, Guowen, Qiu, Han, Guo, Shangwei, Chang, Chip Hong, Zhang, Tianwei
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2023
• Subjects: Computer and Information Science; Profiled Side-Channel Attacks; DNN Accelerator; Sequence-to-Sequence Learning; FPGA; Model Extraction
• Online Access: https://hdl.handle.net/10356/171839; https://fpt2023.org/index.html
• Institution: Nanyang Technological University

DNN accelerators have been widely deployed in many scenarios to speed up the inference process and reduce the energy consumption. One big concern about the usage of the accelerators is the confidentiality of the deployed models: model inference execution on the accelerators could leak side-channel i...