Secure neural network watermarking protocol against forging attack

In order to protect the intellectual property of neural network, an owner may select a set of trigger samples and their corresponding labels to train a network, and prove the ownership by the trigger set without revealing the inner mechanism and parameters of the network. However, if an attacker is...

Full description

Saved in:
Bibliographic Details
Published in:EURASIP journal on image and video processing 2020-09, Vol.2020 (1), p.1-12, Article 37
Main Authors: Zhu, Renjie, Zhang, Xinpeng, Shi, Mengte, Tang, Zhenjun
Format: Article
Language:English
Subjects:
Biometrics
Chains
Engineering
Forgery
Forging
Image Processing and Computer Vision
Labels
Matching
Neural network
Neural networks
New Advances on Intelligent Multimedia Hiding and Forensics
Ownership
Pattern Recognition
Signal,Image and Speech Processing
Trigger set
Watermarking
Watermarking protocol
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!