International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Digital Doppelgangers |
|---|---|
| ABSTRACT | Based on the present globalization, detection of deepfakes is one of the largest challenges in preserving the integrity of digital media. This project designs a deepfake detection system, where a convolutional neural network (CNN) is implemented using TensorFlow and supervised learning to classify images as either "Real" or "Fake." The system has a Deepfake Detector Model and a Dataset Handler, as well as a Flask-based web application that does real-time predictions. The architecture used in the model includes convolutional and pooling layers for extracting features and then dense layers for classification. The train will include preprocessing of the data rescaling and normalization together with callbacks, such as early stopping and learning rate reduction, for better performance. Validating effectiveness, its measures consist of accuracy, precision, and recall. To generate a real fake image, generative adversarial networks integrate well within, augmenting the size of the dataset to improve training robustness. Dataset Handler deals with automating download, unzipping, and data processing. This saves the trained model and puts it in the Flask application, where users can upload images and get their respective classifications. The above implementation explains why TensorFlow-based CNNs have such significant efficacy against GAN-generated deepfake content. |
| AUTHOR | MANOJ KUMAR, LAKSHMI NARASIMHA, DR. K. SRIKALA, DR. K RAJITHA, K. SHIRISHA, MANAS RATH Undergraduate Students, Department of Computer Science and Engineering, Mahatma Gandhi Institute of Technology, Hyderabad, Telangana, India Assistant Professors, Department of Computer Science and Engineering, Mahatma Gandhi Institute of Technology, Hyderabad, Telangana, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405091 |
| pdf/91_Digital Doppelgangers.pdf | |
| KEYWORDS | |
| References | [1] T. Wang, X. Liao, K. P. Chow, X. Lin, and Y. Wang, “Deepfake Detection: A Comprehensive Survey from the Reliability Perspective,” arXiv preprint arXiv:2211.10881, 2022. Available: https://arxiv.org/abs/2211.10881 [2] G. Pei, H. Li, Y. Zhang, X. Chen, and J. Liu,“Deepfake Generation and Detection: A Benchmark and Survey,” arXiv preprint arXiv:2403.17881, 2024. Available: https://arxiv.org/abs/2403.17881 [3] L. Lin, X. He, Y. Ju, X. Wang, and F. Ding, “Preserving Fairness Generalization in Deepfake Detection,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2024. Available: https://openaccess.thecvf.com/content/CVPR2024/html/Lin_Preserving_Fairness_Generalization_in_Deepfake_Detection_CVPR_2024_paper.html [4] Z. Yan, H. Zhang, Y. Liu, X. Chen, and J. Wang, “Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2024. Available: https://openaccess.thecvf.com/content/CVPR2024/html/Yan_Transcending_Forgery_Specificity_with_Latent_Space_Augmentation_for_Generalizable_Deepfake_CVPR_2024_paper.html [5] J. Choi, M. Kim, S. Lee, H. Park, and Y. Jung,“Exploiting Style Latent Flows for Generalizing Deepfake Video Detection,” arXiv preprintarXiv:2403.06592, 2024. Available: https://arxiv.org/abs/2403.06592 [6] M. Li, Q. Zhao, H. Sun, X. Wang, and J. Li,“A Survey on Speech Deepfake Detection,” arXiv preprint arXiv:2404.13914, 2024. Available: https://arxiv.org/abs/2404.13914 [7] F. A. Croitoru, A. Serban, M. Popescu, I. Ionescu, and D. Marinescu,“Deepfake Media Generation and Detection in the Age of Generative AI,” arXiv preprint arXiv:2411.19537, 2024. Available: https://arxiv.org/abs/2411.19537 [8] H. Nguyen-Le, T. Nguyen, P. Tran, Q. Le, and V. Pham,“Passive Deepfake Detection Across Multi-modalities,” arXiv preprint arXiv:2411.17911, 2024. Available: https://arxiv.org/abs/2411.17911 [9] P. Liu, Q. Tao, J. T. Zhou, X. Zhang, and L. Wu,“Evolving from Single-modal to Multi-modal Facial Deepfake Detection: A Survey,” arXiv preprint arXiv:2406.06965, 2024. Available: https://arxiv.org/abs/2406.06965 [10] M. Alrashoud, A. Khan, S. Malik, R. Ahmed, and T. Hussain, “Deepfake Video Detection Methods, Approaches, and Trends,” Expert Systems with Applications, 2025. Available: https://www.sciencedirect.com/science/article/pii/S111001682500465X |
