Fighting Deepfakes Using Body Language Analysis
Recent improvements in deepfake creation have made deepfake videos more realistic. Moreover, open-source software has made deepfake creation more accessible, which reduces the barrier to entry for deepfake creation. This could pose a threat to the people’s privacy. There is a potential danger if the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Forecasting |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-9394/3/2/20 |
| _version_ | 1827693883534868480 |
|---|---|
| author | Robail Yasrab Wanqi Jiang Adnan Riaz |
| author_facet | Robail Yasrab Wanqi Jiang Adnan Riaz |
| author_sort | Robail Yasrab |
| collection | DOAJ |
| description | Recent improvements in deepfake creation have made deepfake videos more realistic. Moreover, open-source software has made deepfake creation more accessible, which reduces the barrier to entry for deepfake creation. This could pose a threat to the people’s privacy. There is a potential danger if the deepfake creation techniques are used by people with an ulterior motive to produce deepfake videos of world leaders to disrupt the order of countries and the world. Therefore, research into the automatic detection of deepfaked media is essential for public security. In this work, we propose a deepfake detection method using upper body language analysis. Specifically, a many-to-one LSTM network was designed and trained as a classification model for deepfake detection. Different models were trained by varying the hyperparameters to build a final model with benchmark accuracy. We achieved 94.39% accuracy on the deepfake test set. The experimental results showed that upper body language can effectively detect deepfakes. |
| first_indexed | 2024-03-10T11:53:34Z |
| format | Article |
| id | doaj.art-f0541faa1f06495489c7f08f9f59103f |
| institution | Directory Open Access Journal |
| issn | 2571-9394 |
| language | English |
| last_indexed | 2024-03-10T11:53:34Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forecasting |
| spelling | doaj.art-f0541faa1f06495489c7f08f9f59103f2023-11-21T17:32:43ZengMDPI AGForecasting2571-93942021-04-013230332110.3390/forecast3020020Fighting Deepfakes Using Body Language AnalysisRobail Yasrab0Wanqi Jiang1Adnan Riaz2Department of Engineering Science, Institute of Biomedical Engineering, University of Oxford, Oxford OX3 7DQ, UKSchool of Computer Science, University of Nottingham, Nottingham NG8 1BB, UKSchool of Computer Science and Technology, Dalian University of Technology, Dalian 116024, ChinaRecent improvements in deepfake creation have made deepfake videos more realistic. Moreover, open-source software has made deepfake creation more accessible, which reduces the barrier to entry for deepfake creation. This could pose a threat to the people’s privacy. There is a potential danger if the deepfake creation techniques are used by people with an ulterior motive to produce deepfake videos of world leaders to disrupt the order of countries and the world. Therefore, research into the automatic detection of deepfaked media is essential for public security. In this work, we propose a deepfake detection method using upper body language analysis. Specifically, a many-to-one LSTM network was designed and trained as a classification model for deepfake detection. Different models were trained by varying the hyperparameters to build a final model with benchmark accuracy. We achieved 94.39% accuracy on the deepfake test set. The experimental results showed that upper body language can effectively detect deepfakes.https://www.mdpi.com/2571-9394/3/2/20imagingmachine learningdeepfakehuman pose estimationupper body languagecomputer vision |
| spellingShingle | Robail Yasrab Wanqi Jiang Adnan Riaz Fighting Deepfakes Using Body Language Analysis Forecasting imaging machine learning deepfake human pose estimation upper body language computer vision |
| title | Fighting Deepfakes Using Body Language Analysis |
| title_full | Fighting Deepfakes Using Body Language Analysis |
| title_fullStr | Fighting Deepfakes Using Body Language Analysis |
| title_full_unstemmed | Fighting Deepfakes Using Body Language Analysis |
| title_short | Fighting Deepfakes Using Body Language Analysis |
| title_sort | fighting deepfakes using body language analysis |
| topic | imaging machine learning deepfake human pose estimation upper body language computer vision |
| url | https://www.mdpi.com/2571-9394/3/2/20 |
| work_keys_str_mv | AT robailyasrab fightingdeepfakesusingbodylanguageanalysis AT wanqijiang fightingdeepfakesusingbodylanguageanalysis AT adnanriaz fightingdeepfakesusingbodylanguageanalysis |