Volume 13, Issue 8 (August 2026), Pages: 125-135

----------------------------------------------

 Original Research Paper

Investigation of image forgery via adaptive CNN and enhanced error level analysis

 Author(s): 

Mohammad Alsaffar ¹, Diaa Mohammed Uliyan ^2, *, Moham’d Al-Dlalah ³, Bander Nasser Almousa ¹

 Affiliation(s):

¹Department of Information and Computer Science, College of Computer Science and Engineering, University of Hail, Hail 81481, Saudi Arabia
²Department of Information Security, College of Computer Science and Engineering, University of Hail, Hail 81481, Saudi Arabia
³High Diploma of Education, Arts and Humanities College, Applied Science Private University, Amman, Jordan

 Full text

    Full Text - PDF

 * Corresponding Author. 

   Corresponding author's ORCID profile:  https://orcid.org/0000-0002-0777-9729

 Digital Object Identifier (DOI)

 
https://doi.org/10.21833/ijaas.2026.08.012

 Abstract

Detecting image forgery is a significant challenge in digital image forensics, especially given the increasing use of advanced image editing software. This study proposes a new method that integrates Enhanced Error Level Analysis (EELA) with an adaptive Convolutional Neural Network (CNN) model to improve the detection of forged regions in images. Unlike traditional methods such as standard ELA or Residual Pixel Analysis, our approach uses EELA to examine compression artifacts in both original and forged images. Enhanced ELA calculates and displays error-level variations within the image at the pixel level. These features are then used to extract spatial features through an adaptive CNN training model to discriminate tampered regions. The proposed method was thoroughly evaluated on image benchmarks, including CASIA v1.0, CASIA v2.0, the Columbia Image Splicing Detection Dataset, and DEFACTO/IMD. The technique shows strong potential for identifying splicing forgeries. The proposed framework demonstrated superior results and greater resilience to image forgery attacks.

 © 2026 The Authors. Published by IASE.

 This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/).

 Keywords

Image forgery detection, Enhanced error level analysis, Adaptive convolutional neural network, Image splicing, Spatial features

 Article history

Received 3 April 2026, Received in revised form 10 August 2026, Accepted 17 August 2026

 Acknowledgment

This research has been supported by the University of Hail, Saudi Arabia. 

 Compliance with ethical standards

 Citation:

Alsaffar M, Uliyan DM, Al-Dlalah M, and Almousa BN (2026). Investigation of image forgery via adaptive CNN and enhanced error level analysis. International Journal of Advanced and Applied Sciences, 13(8): 125-135

  Permanent Link to this page

---------------------------------------------- 

 References (17)

1. Biswas S, Islam MA, Rout J, Mishra M, and Muduli D (2024). Passive image forgery detection through ensemble learning with ELA. In the 2024 International Conference on Computer, Electronics, Electrical Engineering & Their Applications (IC2E3), IEEE, Srinagar Garhwal, Uttarakhand, India: 1-6. https://doi.org/10.1109/IC2E362166.2024.10827508   [Google Scholar]
2. Choudhary RR, Paliwal S, and Meena G (2024). Image forgery detection system using VGG16 UNET model. Procedia Computer Science, 235: 735-744. https://doi.org/10.1016/j.procs.2024.04.070   [Google Scholar]
3. Das D, Naskar R, and Chakraborty RS (2026). Image splicing localization based on Hellinger distance and noise estimation through convolutional neural network and vision transformer. Digital Signal Processing, 168(Part B): 105559. https://doi.org/10.1016/j.dsp.2025.105559   [Google Scholar]
4. Dell’Olmo PV, Kuznetsov O, Frontoni E, Arnesano M, Napoli C, and Randieri C (2025). Dataset dependency in CNN-based copy-move forgery detection: A multi-dataset comparative analysis. Machine Learning and Knowledge Extraction, 7(2): 54. https://doi.org/10.3390/make7020054   [Google Scholar]
5. Dong J, Wang W, and Tan T (2013). CASIA image tampering detection evaluation database. In the 2013 IEEE China Summit and International Conference on Signal and Information Processing, IEEE, Beijing, China: 422-426. https://doi.org/10.1109/ChinaSIP.2013.6625374   [Google Scholar]
6. Hsu YF and Chang SF (2006). Detecting image splicing using geometry invariants and camera characteristics consistency. In the 2006 IEEE International Conference on Multimedia and Expo, IEEE, Toronto, ON, Canada: 549-552. https://doi.org/10.1109/ICME.2006.262447   [Google Scholar] PMid:16739096
7. Jain S and Singh D (2023). VGG16Unet: Effective passive model for image splicing forgery localization. Journal of Electronic Imaging, 32(4): 043015. https://doi.org/10.1117/1.JEI.32.4.043015   [Google Scholar]
8. Kaur N (2025). Hybrid image splicing detection: Integrating CLAHE, improved CNN, and SVM for digital image forensics. Expert Systems with Applications, 273: 126756. https://doi.org/10.1016/j.eswa.2025.126756   [Google Scholar]
9. Khalil AH, Ghalwash AZ, Elsayed HAG, Salama GI, and Ghalwash HA (2023). Enhancing digital image forgery detection using transfer learning. IEEE Access, 11: 91583-91594. https://doi.org/10.1109/ACCESS.2023.3307357   [Google Scholar]
10. Mahfoudi G, Tajini B, Retraint F, Morain-Nicolier F, Dugelay JL, and Pic M (2019). DEFACTO: Image and face manipulation dataset. In the 2019 27th European Signal Processing Conference (EUSIPCO), IEEE, A Coruna, Spain: 1-5. https://doi.org/10.23919/EUSIPCO.2019.8903181   [Google Scholar]
11. Sohail S, Sajjad SM, Zafar A, Iqbal Z, Muhammad Z, and Kazim M (2025). Deepfake image forensics for privacy protection and authenticity using deep learning. Information, 16(4): 270. https://doi.org/10.3390/info16040270   [Google Scholar]
12. Tram PN, Nguyen CT, Le CT, Le DT, and Huynh KT (2025). Combining ELA and frequency analysis for robust classification of authentic, spliced and diffusion image. In the 2025 RIVF International Conference on Computing and Communication Technologies (RIVF), IEEE, Ho Chi Minh City, Vietnam: 623-628. https://doi.org/10.1109/RIVF68649.2025.11365152   [Google Scholar]
13. Uliyan DM, Jalab HA, Abdul Wahab AW, and Sadeghi S (2016a). Image region duplication forgery detection based on angular radial partitioning and Harris key-points. Symmetry, 8(7): 62. https://doi.org/10.3390/sym8070062   [Google Scholar]
14. Uliyan DM, Jalab HA, Wahab AWA, Shivakumara P, and Sadeghi S (2016b). A novel forged blurred region detection system for image forensic applications. Expert Systems with Applications, 64: 1-10. https://doi.org/10.1016/j.eswa.2016.07.026   [Google Scholar]
15. Vaishali S and Neetu S (2024). Enhanced copy-move forgery detection using deep convolutional neural network (DCNN) employing the ResNet-101 transfer learning model. Multimedia Tools and Applications, 83: 10839-10863. https://doi.org/10.1007/s11042-023-15724-z   [Google Scholar]
16. Verma A, Pandey P, and Khari M (2024). ELA-Conv: Forgery detection in digital images based on ELA and CNN. In: Santosh K et al. (Eds.), Recent trends in image processing and pattern recognition: 213–226. Springer, Cham, Switzerland. https://doi.org/10.1007/978-3-031-53082-1_18   [Google Scholar]
17. Yang Y, He Y, Ma X, Lv W, Chen J, and Wang H (2025). AMSEANet: An edge-guided adaptive multi-scale network for image splicing detection and localization. Sensors, 25(20): 6494. https://doi.org/10.3390/s25206494   [Google Scholar] PMid:41157548 PMCid:PMC12568058