Investigating vulnerability of watermarking neural network
A neural network with great performance often incurs a high cost to train. The data used to train a neural network can be confidential or need additional substantial processing. Hence, a trained neural network is regarded as intellectual property. To protect a neural network from infringement of i...
Saved in:
Main Author: | Chua, Viroy Sheng Yang |
---|---|
Other Authors: | Anupam Chattopadhyay |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/138234 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Embedding watermarks into deep neural networks of audio classification
by: Chin, Jun Ying
Published: (2021) -
Exploring the vulnerabilities and enhancing the adversarial robustness of deep neural networks
by: Bai, Tao
Published: (2022) -
An investigation of the application of graph neural networks in recommendation systems
by: Koh, Jaylene Jia Ying
Published: (2023) -
Investigations in neural network learning using geometrical approach
by: Wang, Di
Published: (2008) -
Investigating the causes of the vulnerability of CNNs to adversarial perturbations: learning objective, model components, and learned representations
by: Coppola, Davide
Published: (2023)