DNNobfus: a study on obfuscation-based edge-side model protection framework
The proliferation of artificial intelligence models has rendered them vulnerable to a myriad of security threats. The extensive integration of deep learning models into edge devices has introduced novel security challenges. Given the analogous structural characteristics of deep neural networks, adve...
Saved in:
Main Authors: | SONG Feiyang, ZHAO Xinmiao, YAN Fei, CHENG Binlin, ZHANG Liqiang, YANG Xiaolin, WANG Yang |
---|---|
Format: | Article |
Language: | English |
Published: |
POSTS&TELECOM PRESS Co., LTD
2024-04-01
|
Series: | 网络与信息安全学报 |
Subjects: | |
Online Access: | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2024019 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Review of path branch obfuscation
by: Pu GENG, et al.
Published: (2020-04-01) -
Metrics for code obfuscation based on symbolic execution and N-scope complexity
by: Yuqiang XIAO, et al.
Published: (2022-12-01) -
Anti-obfuscation Android application similarity detection method based on API call
by: Jieming GU, et al.
Published: (2018-01-01) -
Trajectory privacy protection mechanism of obfuscating paths based on vehicles cooperation
by: Ziwen ZHAO, et al.
Published: (2019-08-01) -
An obfuscate implementation for Android resources index table
by: Yang LIU, et al.
Published: (2016-10-01)