Time to leak : cross-device timing attack on edge deep learning accelerator

Time to leak : cross-device timing attack on edge deep learning accelerator

Edge deep learning accelerators are optimised hard ware to enable efficient inference on the edge. The models deployed on these accelerators are often proprietary and thus sensitive for commercial and privacy reasons. In this paper, we demonstrate practical vulnerability of deployed deep learning mo...

Full description

Bibliographic Details
Main Authors: Won, Yoo-Seung, Chatterjee, Soham, Jap, Dirmanto, Bhasin, Shivam, Basu, Arindam
Other Authors: School of Electrical and Electronic Engineering
Format: Conference Paper
Language:English
Published: 2021
Subjects:
Engineering::Computer science and engineering::Information systems::Information systems applications
Deep Learning
Performance Evaluation
Online Access:https://hdl.handle.net/10356/147150

Internet

https://hdl.handle.net/10356/147150

Similar Items