Pruning in face forgery detection
With the rise of deep learning and modern technology, Deepfake algorithms can be used to easily forge fake faces that are so realistic and difficult to distinguish by the human eye. This poses a significant threat to information security as attackers have more power to control and manipulate one’s i...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/165852 |
| _version_ | 1824454676782776320 |
|---|---|
| author | Lam, Zhi Fah |
| author2 | Lin Guosheng |
| author_facet | Lin Guosheng Lam, Zhi Fah |
| author_sort | Lam, Zhi Fah |
| collection | NTU |
| description | With the rise of deep learning and modern technology, Deepfake algorithms can be used to easily forge fake faces that are so realistic and difficult to distinguish by the human eye. This poses a significant threat to information security as attackers have more power to control and manipulate one’s identity to achieve their malicious purposes. To combat this increasingly relevant issue, multiple state-of-the-art Face Forgery detection algorithms have been developed, and many have achieved impressive results when put to the test. However, these algorithms often utilise deep Convolutional Neural Networks (CNN) and the high complexity and computational resources required makes it difficult for one to implement them in a production environment.
In this project, we researched on multiple network pruning methodologies and applied these findings on a publicly available Face Forgery detection algorithm known as LipForensics. With the aim of compressing the model’s size while maintaining its accuracy and performance, we hope to achieve speedup of in model inference time and decrease in the model size. |
| first_indexed | 2025-02-19T03:26:06Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/165852 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:26:06Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1658522023-04-14T15:37:43Z Pruning in face forgery detection Lam, Zhi Fah Lin Guosheng School of Computer Science and Engineering gslin@ntu.edu.sg Engineering::Computer science and engineering With the rise of deep learning and modern technology, Deepfake algorithms can be used to easily forge fake faces that are so realistic and difficult to distinguish by the human eye. This poses a significant threat to information security as attackers have more power to control and manipulate one’s identity to achieve their malicious purposes. To combat this increasingly relevant issue, multiple state-of-the-art Face Forgery detection algorithms have been developed, and many have achieved impressive results when put to the test. However, these algorithms often utilise deep Convolutional Neural Networks (CNN) and the high complexity and computational resources required makes it difficult for one to implement them in a production environment. In this project, we researched on multiple network pruning methodologies and applied these findings on a publicly available Face Forgery detection algorithm known as LipForensics. With the aim of compressing the model’s size while maintaining its accuracy and performance, we hope to achieve speedup of in model inference time and decrease in the model size. Bachelor of Engineering (Computer Science) 2023-04-13T07:50:35Z 2023-04-13T07:50:35Z 2023 Final Year Project (FYP) Lam, Z. F. (2023). Pruning in face forgery detection. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/165852 https://hdl.handle.net/10356/165852 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Lam, Zhi Fah Pruning in face forgery detection |
| title | Pruning in face forgery detection |
| title_full | Pruning in face forgery detection |
| title_fullStr | Pruning in face forgery detection |
| title_full_unstemmed | Pruning in face forgery detection |
| title_short | Pruning in face forgery detection |
| title_sort | pruning in face forgery detection |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/165852 |
| work_keys_str_mv | AT lamzhifah pruninginfaceforgerydetection |