A Hybrid CNN–ViT Deep Learning Framework for Detecting and Classifying Image Manipulation in Online News Media
Main Article Content
Abstract
The tremendous growth in the flow of information online, and its quick evolution in the digital age has led to serious challenges. Fake news, particularly that which relies on dubious or manipulated images (such as using Adobe Photoshop or GAN networks), deepfake techniques, has become a clear danger to credibility and public opinion are among the most dangerous practice of media manipulation, because to their ability to directly influence the public and weaken trust in media sources and news organizations .The purpose of this work was to develop a hybrid system model for detecting misleading and manipulated images on online news websites. This was through an integrated model based on the Vision transducer (ViT) combined a model that integrates with convolutional neural networks (ResNet50 and EfficientNetB3).The suggested model leverages the capabilities of convolutional the networks for feature extraction and the analysis of long-range relevance inside an image, utilizing the capabilities of the Vision Transducer. This provides for more accurate visual portrayal. The model was developed using pre-trained weights and translational learning, and then father enhanced by adding leakage layers to reduce over-allocation. The proposed model was training and achieved a test accuracy of 78.2%. The stability of performance during the verification phase confirms the model’s effectiveness and reliability in verifying the authenticity of images in digital media before publication.
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
[1] H. F. Shahzad, F. Rustam, E. S. Flores, J. Luís Vidal Mazón, I. de la Torre Diez, and I. Ashraf, “A Review of Image Processing Techniques for Deepfakes,” Sensors, vol. 22, no. 12, 2022, doi: https://doi.org/10.3390/s22124556 .
[2] S. Shah and S. Patel, “A Comprehensive Survey on Fake News Detection Using Machine Learning,” Journal of Computer Science, vol. 21, no. 4, pp. 982–990, 2025, doi: https://doi.org/10.3844/jcssp.2025.982.990 .
[3] M. S. Rana, M. N. Nobi, B. Murali, and A. H. Sung, “Deepfake Detection: A Systematic Literature Review,” IEEE Access, vol. 10, pp. 25494–25513, 2022, doi: 10.1109/ACCESS.2022.3154404.
[4] M. R. A.-R. Hussein Ala’a Al-Kaabi, Ali Nadhim Kamber, Ali Kadhim Jasim, “Fake News Detection: A Comprehensive Taxonomy of Text, Image, Video, and Multi-Modal Techniques,” Alkadhim Journal for Computer Science, vol. 3, no. 2, 2025, doi: https://doi.org/10.61710/kjcs.v3i2.103 .
[5] P. A. A. Takasu, “Emotional Bots: Content-based Spammer Detection on Social Media,” IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1–8, 2018, doi: 10.1109/WIFS.2018.8630760.
[6] V. S. Sadanand, S. S. Janardhana, S. Purushothaman, S. Hande, and R. Prakash, “Convolutional neural network-based techniques and error level analysis for image tamper detection,” 2024. doi: 10.11591/ijeecs.v33.i2.pp1100-1107.
[7] G. Mu, J. Dai, C. Li, and J. Li, “IBKA-MSM: A Novel Multimodal Fake News Detection Model Based on Improved Swarm Intelligence Optimization Algorithm, Loop-Verified Semantic Alignment and Confidence-Aware Fusion,” Biomimetics, vol. 10, no. 11, Nov. 2025, doi: 10.3390/biomimetics10110782.
[8] E. I. Setiawan et al., “An image and text-based fake news detection with transfer learning,” PLoS One, vol. 20, no. 6 June, Jun. 2025, doi:https://doi.org/10.1371/journal.pone.0324394 .
[9] J. Y. and I. E. D. Afchar, V. Nozick, “MesoNet: a Compact Facial Video Forgery Detection Network,” IEEE International Workshop on Information Forensics and Security (WIFS), 2018, doi: 10.1109/WIFS.2018.8630761.
[10] K. Alshammari, H. & Elleithy, “Deep Fake and Digital Forensics,” IEEE 14th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), pp. 0283–0288, 2023, doi: 10.1109/UEMCON59035.2023.10315974.
[11] J. Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, “Deepfakes and beyond: A Survey of face manipulation and fake detection,” Information Fusion, vol. 64, pp. 131–148, 2020, doi: https://doi.org/10.1016/J.INFFUS.2020.06.014 .
[12] M. A. (2024) Qureshi, S., Saeed, A., Almotiri, S. H., Ahmad, F., & Al Ghamdi, “Deepfake forensics: a survey of digital forensic methods for multimodal deepfake identification on social media,” PeerJ Comput. Sci., vol. 10, e2037, 2024, doi: 10.7717/peerj-cs.2037.
[13] J. T. and M. N. A. Rössler, D. Cozzolino, L. Verdoliva, C. Riess, “FaceForensics++: Learning to Detect Manipulated Facial Images,” IEEE/CVF International Conference on Computer Vision (ICCV), pp. 1–11, 2019, doi: 10.1109/ICCV.2019.00009.
[14] A. A. Wang, S.-Y., Wang, O., Zhang, R., Owens, A., & Efros, “CNN-Generated Images Are Surprisingly Easy to Spot… for Now,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8692–8701, 2020, doi: 10.1109/CVPR42600.2020.00872.
[15] M. S. (n. d. Raza, S. A., Habib, U., Usman, M., Cheema, A. A., & Khan, “MMGANGuard: A Robust Approach for Detecting Fake Images Generated by GANs using Multi-Model Techniques,” IEEE Access, vol. 12, pp. 104153–104164, 2024, doi: https://doi.org/10.1109/access.2024.3393842.
[16] T. Wu, J., Feng, K., Chang, X., & Yang, “A Forensic Method for DeepFake Image based on Face Recognition,” International Conference on Big Data, pp. 104–108, 2020, doi: https://doi.org/10.1145/3409501.3409544.
[17] I. Noreen, M. S. Muneer, and S. Gillani, “Deepfake attack prevention using steganography GANs,” PeerJ Comput. Sci., vol. 8, p. e1125, 2022, doi: 10.7717/peerj-cs.1125.
[18] Mrs. P. S, “DeepFake Image Detection,” Interantional Journal of Scientific Research in Engineering and Management, vol. 08, no. 04, pp. 1–5, 2024, doi: 10.55041/ijsrem30215.
[19] J. Ghita, B., Kuzminykh, I., Usama, A., Bakhshi, T., & Marchang, “Deepfake Image Detection Using Vision Transformer Models,” 2024 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom), Tbilisi, Georgia, pp. 332–335, 2024, doi: 10.1109/BlackSeaCom61746.2024.10646310.
[20] M. Zhu, M. Li, and Z. Wang, “Image tampering detection based on RDS-YOLOv5 feature enhancement transformation,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-76388-9.