Fighting against deepfakes in the wild
Deepfakes are fake media generated by deep learning models. Deepfakes can easily give attackers the ability to control one's identity. Hence, attackers can make use of deepfakes to achieve their malicious purposes such as defamation and spreading misinformation. As deepfake generation tools...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/156692 |
| _version_ | 1826123238632062976 |
|---|---|
| author | Chen, Xinyi |
| author2 | Liu Yang |
| author_facet | Liu Yang Chen, Xinyi |
| author_sort | Chen, Xinyi |
| collection | NTU |
| description | Deepfakes are fake media generated by deep learning models. Deepfakes can easily give attackers the ability to control one's identity. Hence, attackers can make use of deepfakes to achieve their malicious purposes such as defamation and spreading misinformation.
As deepfake generation tools become more and more readily available, the threat posed by deepfakes looms large. Therefore, it is crucial to develop new ideas to detect deepfakes. The Trusted Media Challenge organized by AI Singapore has given us the chance to explore deepfake detection methods. By participating in this challenge, our team has had the opportunity to attempt to solve fake face detection, fake voice detection and inconsistency detection. This report aims to summarize the models and techniques used for each kind of deepfake detection. |
| first_indexed | 2024-10-01T06:01:23Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/156692 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:01:23Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1566922022-04-22T05:57:18Z Fighting against deepfakes in the wild Chen, Xinyi Liu Yang School of Computer Science and Engineering yangliu@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Deepfakes are fake media generated by deep learning models. Deepfakes can easily give attackers the ability to control one's identity. Hence, attackers can make use of deepfakes to achieve their malicious purposes such as defamation and spreading misinformation. As deepfake generation tools become more and more readily available, the threat posed by deepfakes looms large. Therefore, it is crucial to develop new ideas to detect deepfakes. The Trusted Media Challenge organized by AI Singapore has given us the chance to explore deepfake detection methods. By participating in this challenge, our team has had the opportunity to attempt to solve fake face detection, fake voice detection and inconsistency detection. This report aims to summarize the models and techniques used for each kind of deepfake detection. Bachelor of Engineering (Computer Science) 2022-04-22T05:57:18Z 2022-04-22T05:57:18Z 2022 Final Year Project (FYP) Chen, X. (2022). Fighting against deepfakes in the wild. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156692 https://hdl.handle.net/10356/156692 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Chen, Xinyi Fighting against deepfakes in the wild |
| title | Fighting against deepfakes in the wild |
| title_full | Fighting against deepfakes in the wild |
| title_fullStr | Fighting against deepfakes in the wild |
| title_full_unstemmed | Fighting against deepfakes in the wild |
| title_short | Fighting against deepfakes in the wild |
| title_sort | fighting against deepfakes in the wild |
| topic | Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
| url | https://hdl.handle.net/10356/156692 |
| work_keys_str_mv | AT chenxinyi fightingagainstdeepfakesinthewild |