A Decision-Fusion Framework for Digital Image Forgery Detection Using Deep Feature Learning
Keywords:
Digital image forensics, Image forgery detection, Passive image authentication, Decision-level fusion, Deep learning, Support vector machine, Convolutional neural networksAbstract
Digital image manipulation has become increasingly sophisticated due to the rapid advancement of image editing software and the pervasive dissemination of visual content through online platforms. As a result, ensuring the authenticity and integrity of digital images has emerged as a critical challenge in digital forensics. In scenarios where active protection mechanisms such as watermarks or digital signatures are unavailable, passive (blind) image forgery detection techniques provide an effective alternative. This paper proposes a robust decision-level fusion framework for detecting digital image forgeries by integrating deep learning–based feature extraction with classical machine learning classifiers.
The proposed framework evaluates a diverse set of convolutional neural network (CNN) architectures, including spatial exploitation networks, lightweight models, and residual networks, to extract discriminative deep features from images. Experiments are conducted on three widely used benchmark datasets—MICC-F220, Columbia, and CoMoFoD. For each dataset, the top-performing CNN models are fine-tuned using different optimization strategies, including stochastic gradient descent with momentum (SGDM), Adam, and RMSprop. The extracted features are fused at the decision level and classified using a support vector machine (SVM).
Extensive experimental results demonstrate that the proposed fusion-based approach significantly improves detection accuracy and robustness while reducing false positive rates. The framework consistently outperforms individual deep learning models and existing state-of-the-art methods across all datasets, confirming its effectiveness for real-world image forgery detection applications.
References
M. Verma and D. Singh, “Survey on image copy-move forgery detection,” *Multimedia Tools Appl.*, vol. 83, pp. 23761–23797, 2024. :contentReference[oaicite:13]{index=13}
N. E. B. Amara, “Image forgery detection with focus on copy-move: An overview, real world challenges and future directions,” *Appl. Sci.*, vol. 15, no. 21, p. 11774, 2025. :contentReference[oaicite:14]{index=14}
Z. S. Ibrahim and T. M. Hasan, “Copy-move image forgery detection using deep learning approaches: An abbreviated survey,” *Bilad Alrafidain J. Eng. Sci. Technol.*, vol. 4, no. 1, pp. 137–154, 2025. :contentReference[oaicite:15]{index=15}
K. Rehman, “Detection of copy-move forgery with deep CNN features,” *Procedia Comput. Sci.*, 2025. :contentReference[oaicite:16]{index=16}
A. U. Shehin, “Copy-move forgery detection and localisation robust to complex scenarios,” 2024. :contentReference[oaicite:17]{index=17}
B. Gholap et al., “Enhanced copy-move forgery detection in images using hybrid deep learning approach,” 2025. :contentReference[oaicite:18]{index=18}
Y. Li *et al.*, “Image copy-move forgery detection via deep PatchMatch and pairwise ranking learning,” *IEEE Trans. Image Process.*, vol. 34, no. 4, 2025. :contentReference[oaicite:19]{index=19}
L. Jiang *et al.*, “MSN: Multi-directional similarity network for hand-crafted and deep-synthesized copy-move forgery detection,” arXiv:2512.07110, 2025. :contentReference[oaicite:20]{index=20}
Y. Liu *et al.*, “CMFDFormer: Transformer-based copy-move forgery detection with continual learning,” arXiv:2311.13263, 2023. :contentReference[oaicite:21]{index=21}
Z. S. Ibrahim, “Copy-Move image forgery detection using forensic images and deep learning,” 2025. :contentReference[oaicite:22]{index=22}
D. Fischinger and M. Boyer, “DF2023: The digital forensics 2023 dataset for image forgery detection,” arXiv:2503.22417, 2025. :contentReference[oaicite:23]{index=23}
B. Benmessahel, “Deep learning methods for copy move image forgery detection: A review,” IIETA, 2024. :contentReference[oaicite:24]{index=24}
M. E. Mahdi and N. H. M. Ali, “Copy-move image forgery detection using multi-level LBP algorithm,” *J. Eng.*, 2024. :contentReference[oaicite:25]{index=25} [11] M. Bilal, H. A. Habib, Z. Mehmood, R. M. Yousaf, T. Saba, and A. Rehman, “A robust technique for copy-move forgery detection from small and extremely smooth tampered regions based on the dhe-surf features and mdbscan clustering,” Australian Journal of Forensic Sciences, pp. 1–24, 2020.
G. Gani and F. Qadir, “A robust copy-move forgery detection technique based on discrete cosine transform and cellular automata,” Journal of Information Security and Applications, vol. 54, p. 102510, 2020.
Z. J. Barad and M. M. Goswami, “Image forgery detection using deep learning: A survey,” in 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS). IEEE, 2020, pp. 571–576.
D. Chauhan, D. Kasat, S. Jain, and V. Thakare, “Survey on keypoint based copy-move forgery detection methods on image,” Procedia Computer Science, vol. 85, pp. 206–212, 2016.
T. Le-Tien, H. Phan-Xuan, T. Nguyen-Chinh, and T. Do-Tieu, “Image forgery detection: A low computational-cost and effective data-driven model,” International Journal of Machine Learning and Computing, vol. 9, no. 2, 2019.
A. K. Chakraverti and V. Dhir, “A hybrid approach to find cloned objects in copy move forged images,” International Journal of Forensic Software Engineering, vol. 1, no. 1, pp. 3–20, 2019.
D.-H. Kim and H.-Y. Lee, “Image manipulation detection using convolutional neural network,” International Journal of Applied Engineering Research, vol. 12, no. 21, pp. 11 640–11 646, 2017.
J. Chen, X. Kang, Y. Liu, and Z. J. Wang, “Median filtering forensics based on convolutional neural networks,” IEEE Signal Processing Letters, vol. 22, no. 11, pp. 1849–1853, 2015.
N. B. Abd Warif, A. W. A. Wahab, M. Y. I. Idris, R. Ramli, R. Salleh, S. Shamshirband, and K.-K. R. Choo, “Copy-move forgery detection: survey, challenges and future directions,” Journal of Network and Computer Applications, vol. 75, pp. 259–278, 2016.
Y. Li and J. Zhou, “Fast and effective image copy-move forgery detection via hierarchical feature point matching,” IEEE Transactions on Information Forensics and Security, vol. 14, no. 5, pp. 1307–1322, 2018.
S. Teerakanok and T. Uehara, “Copy-move forgery detection: A state-of-the-art technical review and analysis,” IEEE Access, vol. 7, pp. 40 550–40 568, 2019.
