Physical unclonable function anti-counterfeiting labels with deep learning authentication
Physical Unclonable Function (PUF) is a recently developed anti-counterfeiting technique. the ability to generate strong anti-counterfeiting tags is the main reason for its vast development. Mostly, Convolutional Neural Network is used to authenticate these anti-counterfeiting tags due to its abi...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/163592 |
| _version_ | 1826119586478555136 |
|---|---|
| author | Sebastian, James |
| author2 | Y. C. Chen |
| author_facet | Y. C. Chen Sebastian, James |
| author_sort | Sebastian, James |
| collection | NTU |
| description | Physical Unclonable Function (PUF) is a recently developed anti-counterfeiting technique.
the ability to generate strong anti-counterfeiting tags is the main reason for its vast development.
Mostly, Convolutional Neural Network is used to authenticate these anti-counterfeiting tags due to
its ability to automatically extract input image features. However, a very deep convolutional neural
network must deal with overfitting. In the PUF authentication process, the main cause of
overfitting is the minor alteration of PUF tags by a flow of time.
In this project, the Resnet-feature extraction pair model is proposed to deal with the overfitting
problem. The Resnet-feature extraction pair model combined extracted features from a convolution
neural network and extracted features from the mathematical computation. Subsequently, these
features are used to fit the Support Vector Machine. To evaluate its compatibility, the Resnet-feature
extraction pair model is implemented in PUF authentication process by using 8 true PUF tags and
356 fake PUF tags.
As a result, the Resnet-feature extraction pair model achieved a 15% accuracy improvement.
Hence, it can be concluded that the Resnet-feature extraction pair model is a considerable tool for
PUF authentication. |
| first_indexed | 2024-10-01T05:02:49Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/163592 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:02:49Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1635922023-07-07T19:01:43Z Physical unclonable function anti-counterfeiting labels with deep learning authentication Sebastian, James Y. C. Chen School of Electrical and Electronic Engineering yucchen@ntu.edu.sg Engineering::Electrical and electronic engineering Physical Unclonable Function (PUF) is a recently developed anti-counterfeiting technique. the ability to generate strong anti-counterfeiting tags is the main reason for its vast development. Mostly, Convolutional Neural Network is used to authenticate these anti-counterfeiting tags due to its ability to automatically extract input image features. However, a very deep convolutional neural network must deal with overfitting. In the PUF authentication process, the main cause of overfitting is the minor alteration of PUF tags by a flow of time. In this project, the Resnet-feature extraction pair model is proposed to deal with the overfitting problem. The Resnet-feature extraction pair model combined extracted features from a convolution neural network and extracted features from the mathematical computation. Subsequently, these features are used to fit the Support Vector Machine. To evaluate its compatibility, the Resnet-feature extraction pair model is implemented in PUF authentication process by using 8 true PUF tags and 356 fake PUF tags. As a result, the Resnet-feature extraction pair model achieved a 15% accuracy improvement. Hence, it can be concluded that the Resnet-feature extraction pair model is a considerable tool for PUF authentication. Bachelor of Engineering (Electrical and Electronic Engineering) 2022-12-12T04:45:58Z 2022-12-12T04:45:58Z 2022 Final Year Project (FYP) Sebastian, J. (2022). Physical unclonable function anti-counterfeiting labels with deep learning authentication. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/163592 https://hdl.handle.net/10356/163592 en A2399-212 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Sebastian, James Physical unclonable function anti-counterfeiting labels with deep learning authentication |
| title | Physical unclonable function anti-counterfeiting labels with deep learning authentication |
| title_full | Physical unclonable function anti-counterfeiting labels with deep learning authentication |
| title_fullStr | Physical unclonable function anti-counterfeiting labels with deep learning authentication |
| title_full_unstemmed | Physical unclonable function anti-counterfeiting labels with deep learning authentication |
| title_short | Physical unclonable function anti-counterfeiting labels with deep learning authentication |
| title_sort | physical unclonable function anti counterfeiting labels with deep learning authentication |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/163592 |
| work_keys_str_mv | AT sebastianjames physicalunclonablefunctionanticounterfeitinglabelswithdeeplearningauthentication |