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

• المؤلفون الرئيسيون: Yan, Xiaobei, Lou, Xiaoxuan, Xu, Guowen, Qiu, Han, Guo, Shangwei, Chang, Chip Hong, Zhang, Tianwei
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: Conference or Workshop Item
• اللغة: English
• منشور في: 2023
• الموضوعات: Computer and Information Science; Profiled Side-Channel Attacks; DNN Accelerator; Sequence-to-Sequence Learning; FPGA; Model Extraction
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/171839; https://fpt2023.org/index.html
• المؤسسة: 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...