Fingerprinting deep neural networks - a DeepFool approach
A well-trained deep learning classifier is an expensive intellectual property of the model owner. However, recently proposed model extraction attacks and reverse engineering techniques make model theft possible and similar quality deep learning solution reproducible at a low cost. To protect the int...
Saved in:
Main Authors: | Wang, Si, Chang, Chip Hong |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/147023 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Deep learning network security
by: Wang, Si, et al.
Published: (2021) -
Inconspicuous data augmentation based backdoor attack on deep neural networks
by: Xu, Chaohui, et al.
Published: (2023) -
DEEP NEURAL NETWORKS
by: BENJAMIN FRANCK CHRISTOPHE SCELLIER
Published: (2015) -
On training deep neural networks using a streaming approach
by: Duda, Piotr, et al.
Published: (2020) -
ROBUST LEARNING AND PREDICTION IN DEEP LEARNING
by: ZHANG JINGFENG
Published: (2021)