Effects of incremental training on watermarked neural networks
Deep learning has achieved extraordinary results in many different areas, ranging from autonomous driving [1], medical devices [2] to speech recognition and natural language processing [3]. Generating a high-performance neural network is costly in aspects of time, computational resources, and exp...
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project (FYP) |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/167143 |
_version_ | 1811683151247835136 |
---|---|
author | Heng, Chuan Song |
author2 | Anupam Chattopadhyay |
author_facet | Anupam Chattopadhyay Heng, Chuan Song |
author_sort | Heng, Chuan Song |
collection | NTU |
description | Deep learning has achieved extraordinary results in many different areas, ranging from autonomous
driving [1], medical devices [2] to speech recognition and natural language processing
[3]. Generating a high-performance neural network is costly in aspects of time, computational resources,
and expertise, making the models valuable intellectual property (IP). As a result, there has
been a notable growth in attention and investments in the paradigm of machine learning. In recent
years, watermarking methods have been developed in order to protect the Intellectual Property
Rights (IPR) of neural networks, and many schemes have successfully prevented adversaries from
stealing such models. However, little has been studied on how Incremental Training would affect
the persistence of watermarks in such watermarking schemes. This investigation aims to discover
the effects of Incremental Training on in existing watermarking schemes.
Keywords: Intellectual Property Rights (IPR), Watermarking, Incremental Training |
first_indexed | 2024-10-01T04:08:10Z |
format | Final Year Project (FYP) |
id | ntu-10356/167143 |
institution | Nanyang Technological University |
language | English |
last_indexed | 2024-10-01T04:08:10Z |
publishDate | 2023 |
publisher | Nanyang Technological University |
record_format | dspace |
spelling | ntu-10356/1671432023-05-26T15:37:37Z Effects of incremental training on watermarked neural networks Heng, Chuan Song Anupam Chattopadhyay School of Computer Science and Engineering anupam@ntu.edu.sg Engineering::Computer science and engineering Deep learning has achieved extraordinary results in many different areas, ranging from autonomous driving [1], medical devices [2] to speech recognition and natural language processing [3]. Generating a high-performance neural network is costly in aspects of time, computational resources, and expertise, making the models valuable intellectual property (IP). As a result, there has been a notable growth in attention and investments in the paradigm of machine learning. In recent years, watermarking methods have been developed in order to protect the Intellectual Property Rights (IPR) of neural networks, and many schemes have successfully prevented adversaries from stealing such models. However, little has been studied on how Incremental Training would affect the persistence of watermarks in such watermarking schemes. This investigation aims to discover the effects of Incremental Training on in existing watermarking schemes. Keywords: Intellectual Property Rights (IPR), Watermarking, Incremental Training Bachelor of Engineering (Computer Science) 2023-05-23T11:45:36Z 2023-05-23T11:45:36Z 2023 Final Year Project (FYP) Heng, C. S. (2023). Effects of incremental training on watermarked neural networks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/167143 https://hdl.handle.net/10356/167143 en SCSE22-0019 application/pdf Nanyang Technological University |
spellingShingle | Engineering::Computer science and engineering Heng, Chuan Song Effects of incremental training on watermarked neural networks |
title | Effects of incremental training on watermarked neural networks |
title_full | Effects of incremental training on watermarked neural networks |
title_fullStr | Effects of incremental training on watermarked neural networks |
title_full_unstemmed | Effects of incremental training on watermarked neural networks |
title_short | Effects of incremental training on watermarked neural networks |
title_sort | effects of incremental training on watermarked neural networks |
topic | Engineering::Computer science and engineering |
url | https://hdl.handle.net/10356/167143 |
work_keys_str_mv | AT hengchuansong effectsofincrementaltrainingonwatermarkedneuralnetworks |