Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62994
Volume:
10 |
5 |
May 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Science of Engineering
Bharath Instuite of Higher Education and Research
Computer Science of Engineering
Bharath Instuite of Higher Education and Research
Computer Science of Engineering
Bharath Instuite of Higher Education and Research
Deepfakes have become a major danger of the digital age, allowing to produce incredibly realistic manipulated images and videos that can be used to deceive people and affect the veracity of information. The identification of such forged media has become very important because it can be abused in various fields, including social media, cybersecurity, and digital forensics. Despite promising outcomes in deepfake detection, most of the current models have high computational complexity and inability to generalize in a variety of datasets. To resolve these issues, the current paper suggests an effective deep learning architecture to detect deepfakes with the help of the convolutional neural network based on Xception. The model uses the concept of transfer learning to obtain discriminative features within facial regions and successfully categorize the images as real or fake. An initial processing pipeline that includes face detection, resizing and normalization is used to improve model performance. In addition, the system is also trained and tested on the FaceForensics++ dataset, which makes it robust to all forms of manipulation. The experimental findings indicate that the proposed method is highly accurate in the classification and is computationally efficient. There is also a high generalization ability in the model which makes it applicable in real world. This paper will help advance dependable and scalable deepfake detection systems to counter the increasing risk of manipulated media.
KEYWORDS
The presented paper presents an effective deepfake detection system based on the Xception-based deep learning model. The suggested solution is capable of detecting manipulated pictures effectively with the help of transfer learning and sound preprocessing methods. The experimental findings indicate that the model is very generalizes well on diverse data sets. The system is computationally effective and can be invested on the. real world like social media monitoring and digital forensics. The system can be also improved in the future by adding the multi-modal analysis and the real-time optimization to enhance its capacity to fight the deepfake threats.
[1] A. Ro¨ssler, D. Cozzolino, L. Verdoliva, C. Riess, J. Thies, and M. Nießner, “FaceForensics++: Learning to Detect Manipulated Facial Images,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 1–11. [2] F. Chollet, “Xception: Deep Learning with Depthwise Separable Con-volutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1251–1258. [3] D. Afchar, V. Nozick, J. Yamagishi, and I. Echizen, “MesoNet: a Com-pact Facial Video Forgery Detection Network,” in IEEE International Workshop on Information Forensics and Security (WIFS), 2018, pp. 1–7. [4] A. Ro¨ssler, D. Cozzolino, L. Verdoliva, C. Riess, J. Thies, and M. Nießner, “FaceForensics: A Large-Scale Video Dataset for Forgery Detection in Human Faces,” arXiv preprint arXiv:1803.09179, 2018. [5] B. Dolhansky, R. Howes, B. Pflaum, N. Baram, and C. Canton Ferrer, “The Deepfake Detection Challenge Dataset,” arXiv preprint arXiv:2006.07397, 2020. [6] D. Gu¨era and E. J. Delp, “Deepfake Video Detection Using Recurrent Neural Networks,” in IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2018, pp. 1–6. [7] H. H. Nguyen, J. Yamagishi, and I. Echizen, “Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videos,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, pp. 2307–2311. [8] Y. Li, M.-C. Chang, and S. Lyu, “In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking,” in IEEE International Workshop on Information Forensics and Security (WIFS), 2018, pp. 1–7. [9] E. Sabir, J. Cheng, A. Jaiswal, W. AbdAlmageed, I. Masi, and P. Natarajan, “Recurrent Convolutional Strategies for Face Manipulation Detection in Videos,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019, pp. 80–87. [10] R. Tolosana, R. Vera-Rodriguez, J. Fierrez, A. Morales, and J. Ortega-Garcia, “DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection,” Information Fusion, vol. 64, pp. 131–148, 2020.
Publication Date
5/10/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...