A novel approach for detecting deep fake videos using graph neural network
Abstract Deep fake technology has emerged as a double-edged sword in the digital world. While it holds potential for legitimate uses, it can also be exploited to manipulate video content, causing severe social and security concerns. The research gap lies in the fact that traditional deep fake detect...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-02-01
|
| Series: | Journal of Big Data |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40537-024-00884-y |
| _version_ | 1797274293991636992 |
|---|---|
| author | M. M. El-Gayar Mohamed Abouhawwash S. S. Askar Sara Sweidan |
| author_facet | M. M. El-Gayar Mohamed Abouhawwash S. S. Askar Sara Sweidan |
| author_sort | M. M. El-Gayar |
| collection | DOAJ |
| description | Abstract Deep fake technology has emerged as a double-edged sword in the digital world. While it holds potential for legitimate uses, it can also be exploited to manipulate video content, causing severe social and security concerns. The research gap lies in the fact that traditional deep fake detection methods, such as visual quality analysis or inconsistency detection, need help to keep up with the rapidly advancing technology used to create deep fakes. That means there's a need for more sophisticated detection techniques. This paper introduces an enhanced approach for detecting deep fake videos using graph neural network (GNN). The proposed method splits the detection process into two phases: a mini-batch graph convolution network stream four-block CNN stream comprising Convolution, Batch Normalization, and Activation function. The final step is a flattening operation, which is essential for connecting the convolutional layers to the dense layer. The fusion of these two phases is performed using three different fusion networks: FuNet-A (additive fusion), FuNet-M (element-wise multiplicative fusion), and FuNet-C (concatenation fusion). The paper further evaluates the proposed model on different datasets, where it achieved an impressive training and validation accuracy of 99.3% after 30 epochs. |
| first_indexed | 2024-03-07T14:57:21Z |
| format | Article |
| id | doaj.art-4c7c5d5d01ca432e8d0ae4a5cd605373 |
| institution | Directory Open Access Journal |
| issn | 2196-1115 |
| language | English |
| last_indexed | 2024-03-07T14:57:21Z |
| publishDate | 2024-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Big Data |
| spelling | doaj.art-4c7c5d5d01ca432e8d0ae4a5cd6053732024-03-05T19:22:31ZengSpringerOpenJournal of Big Data2196-11152024-02-0111112710.1186/s40537-024-00884-yA novel approach for detecting deep fake videos using graph neural networkM. M. El-Gayar0Mohamed Abouhawwash1S. S. Askar2Sara Sweidan3Department of Information Technology, Faculty of Computers and Information, Mansoura UniversityDepartment of Computational Mathematics, Science and Engineering (CMSE), College of Engineering, Michigan State UniversityDepartment of Statistics and Operations Research, College of Science, King Saud UniversityArtificial Intelligence Department, Faculty of Computer and Artificial Intelligence, Benha UniversityAbstract Deep fake technology has emerged as a double-edged sword in the digital world. While it holds potential for legitimate uses, it can also be exploited to manipulate video content, causing severe social and security concerns. The research gap lies in the fact that traditional deep fake detection methods, such as visual quality analysis or inconsistency detection, need help to keep up with the rapidly advancing technology used to create deep fakes. That means there's a need for more sophisticated detection techniques. This paper introduces an enhanced approach for detecting deep fake videos using graph neural network (GNN). The proposed method splits the detection process into two phases: a mini-batch graph convolution network stream four-block CNN stream comprising Convolution, Batch Normalization, and Activation function. The final step is a flattening operation, which is essential for connecting the convolutional layers to the dense layer. The fusion of these two phases is performed using three different fusion networks: FuNet-A (additive fusion), FuNet-M (element-wise multiplicative fusion), and FuNet-C (concatenation fusion). The paper further evaluates the proposed model on different datasets, where it achieved an impressive training and validation accuracy of 99.3% after 30 epochs.https://doi.org/10.1186/s40537-024-00884-yGraph neural networkConvolutional neural networkDeepfake video detectionMulti-task cascaded convolutional neural networkMini-GNN |
| spellingShingle | M. M. El-Gayar Mohamed Abouhawwash S. S. Askar Sara Sweidan A novel approach for detecting deep fake videos using graph neural network Journal of Big Data Graph neural network Convolutional neural network Deepfake video detection Multi-task cascaded convolutional neural network Mini-GNN |
| title | A novel approach for detecting deep fake videos using graph neural network |
| title_full | A novel approach for detecting deep fake videos using graph neural network |
| title_fullStr | A novel approach for detecting deep fake videos using graph neural network |
| title_full_unstemmed | A novel approach for detecting deep fake videos using graph neural network |
| title_short | A novel approach for detecting deep fake videos using graph neural network |
| title_sort | novel approach for detecting deep fake videos using graph neural network |
| topic | Graph neural network Convolutional neural network Deepfake video detection Multi-task cascaded convolutional neural network Mini-GNN |
| url | https://doi.org/10.1186/s40537-024-00884-y |
| work_keys_str_mv | AT mmelgayar anovelapproachfordetectingdeepfakevideosusinggraphneuralnetwork AT mohamedabouhawwash anovelapproachfordetectingdeepfakevideosusinggraphneuralnetwork AT ssaskar anovelapproachfordetectingdeepfakevideosusinggraphneuralnetwork AT sarasweidan anovelapproachfordetectingdeepfakevideosusinggraphneuralnetwork AT mmelgayar novelapproachfordetectingdeepfakevideosusinggraphneuralnetwork AT mohamedabouhawwash novelapproachfordetectingdeepfakevideosusinggraphneuralnetwork AT ssaskar novelapproachfordetectingdeepfakevideosusinggraphneuralnetwork AT sarasweidan novelapproachfordetectingdeepfakevideosusinggraphneuralnetwork |