Protecting neural networks from adversarial attacks
Deep learning has become very popular in recent years and naturally, there are rising concerns about protecting the Intellectual Property (IP) rights of these models. Building and training deep learning models, such as Convolutional Neural Networks (CNNs), require in-depth technical expertise, compu...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/175191 |
| _version_ | 1826114113276739584 |
|---|---|
| author | Lim, Xin Yi |
| author2 | Anupam Chattopadhyay |
| author_facet | Anupam Chattopadhyay Lim, Xin Yi |
| author_sort | Lim, Xin Yi |
| collection | NTU |
| description | Deep learning has become very popular in recent years and naturally, there are rising concerns about protecting the Intellectual Property (IP) rights of these models. Building and training deep learning models, such as Convolutional Neural Networks (CNNs), require in-depth technical expertise, computational resources, large amounts of data, and time. Hence, the motivation to prevent the theft of such valuable models. There exist two robust frameworks to do so, namely watermarking and locking. Watermarking allows validation of the original ownership of a model, whereas locking aims to encrypt the model such that only authorized access can produce accurate results. This report presents a workflow applying both watermarking and locking techniques to various image classification models and shows how both techniques can work hand in hand without compromising the model’s performance. |
| first_indexed | 2024-10-01T03:33:52Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/175191 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:33:52Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1751912024-04-19T15:42:38Z Protecting neural networks from adversarial attacks Lim, Xin Yi Anupam Chattopadhyay School of Computer Science and Engineering anupam@ntu.edu.sg Computer and Information Science Neural networks Deep learning has become very popular in recent years and naturally, there are rising concerns about protecting the Intellectual Property (IP) rights of these models. Building and training deep learning models, such as Convolutional Neural Networks (CNNs), require in-depth technical expertise, computational resources, large amounts of data, and time. Hence, the motivation to prevent the theft of such valuable models. There exist two robust frameworks to do so, namely watermarking and locking. Watermarking allows validation of the original ownership of a model, whereas locking aims to encrypt the model such that only authorized access can produce accurate results. This report presents a workflow applying both watermarking and locking techniques to various image classification models and shows how both techniques can work hand in hand without compromising the model’s performance. Bachelor's degree 2024-04-19T13:00:12Z 2024-04-19T13:00:12Z 2024 Final Year Project (FYP) Lim, X. Y. (2024). Protecting neural networks from adversarial attacks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175191 https://hdl.handle.net/10356/175191 en SCSE23-0259 application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science Neural networks Lim, Xin Yi Protecting neural networks from adversarial attacks |
| title | Protecting neural networks from adversarial attacks |
| title_full | Protecting neural networks from adversarial attacks |
| title_fullStr | Protecting neural networks from adversarial attacks |
| title_full_unstemmed | Protecting neural networks from adversarial attacks |
| title_short | Protecting neural networks from adversarial attacks |
| title_sort | protecting neural networks from adversarial attacks |
| topic | Computer and Information Science Neural networks |
| url | https://hdl.handle.net/10356/175191 |
| work_keys_str_mv | AT limxinyi protectingneuralnetworksfromadversarialattacks |