DeepSniffer: A DNN Model Extraction Framework Based on Learning Architectural Hints

Ling Liang
Ling Liang
Pengfei Zuo
Pengfei Zuo
Yu Ji
Yu Ji
Xinfeng Xie
Xinfeng Xie
Chang Liu
Chang Liu

ASPLOS '20: Architectural Support for Programming Languages and Operating Systems Lausanne Switzerland March, 2020, pp. 385-399, 2020.

Cited by: 10|Views67
EI

Abstract:

As deep neural networks (DNNs) continue their reach into a wide range of application domains, the neural network architecture of DNN models becomes an increasingly sensitive subject, due to either intellectual property protection or risks of adversarial attacks. Previous studies explore to leverage architecture-level events disposed in ha...More

Code:

Data:

Get fulltext within 24h
Bibtex
Your rating :
0

 

Tags
Comments