Forensic Analysis of AI-Generated Image Alterations Using Metadata Evaluation, ELA, and Noise Pattern Analysis

  • Ferdiansyah Ferdiansyah Universitas Indo Global Mandiri, Indonesia
  • Muhammad Rizki Akbar Deazwara Universitas Indo Global Mandiri, Indonesia
  • Reynaldi Rizki Billanivo Universitas Indo Global Mandiri, Indonesia
  • M. Ardiansyah Universitas Indo Global Mandiri, Indonesia
  • Ilham Ilham Universitas Indo Global Mandiri, Indonesia
DOI: 10.63158/journalisi.v7i4.1362
Keywords: Digital Image Forensics, AI-Generated Images, Metadata Analysis, ELA, Noise Analysis

Abstract

This study develops a forensic workflow to assess the authenticity of digital images, addressing the challenge of distinguishing AI-generated content from real photographs. The goal is to analyze metadata, compression behavior, and noise characteristics to identify synthetic images. The dataset includes eight images: two original Xiaomi 14T Pro photos and six AI-generated variants from Gemini, ChatGPT, and Copilot. Metadata was extracted using ExifTool version 13.25 on Kali Linux, while Error Level Analysis (ELA) and Noise Pattern Analysis (NPA) were performed with consistent parameters on the Forensically platform. Authentic images displayed complete EXIF metadata, uniform compression patterns, and stochastic sensor noise. In contrast, AI-generated images lacked EXIF data, included XMP or C2PA provenance, exhibited localized compression anomalies, and showed smoother, more structured noise patterns. The study presents a practical and reproducible forensic workflow that integrates metadata evaluation, ELA, and noise analysis to detect synthetic content. The findings demonstrate that despite their visual realism, AI-generated images still leave detectable forensic traces, offering valuable tools for image authenticity verification.

Downloads

Download data is not yet available.

References

S.-Y. Wang, O. Wang, R. Zhang, A. Owens, and A. A. Efros, “CNN-generated images are surprisingly easy to spot... for now,” Apr. 2020. doi: 10.48550/arXiv.1912.11035.

L. Verdoliva, “Media Forensics and DeepFakes: an overview,” Jan. 2020. doi: 10.48550/arXiv.2001.06564.

A. Näslund, “Image metadata. From information management to interpretative practice,” Museum Management and Curatorship, vol. 39, no. 4, pp. 398–418, Jul. 2024, doi: 10.1080/09647775.2022.2073562.

H. T. Sencar and N. Memon, “Overview of State-of-the-Art in Digital Image Forensics,” in Algorithms, Architectures and Information Systems Security, vol. Volume 3, in Statistical Science and Interdisciplinary Research, vol. Volume 3. , WORLD SCIENTIFIC, 2008, pp. 325–347. doi: 10.1142/9789812836243_0015.

J. A. Redi, W. Taktak, and J.-L. Dugelay, “Digital image forensics: a booklet for beginners,” Multimed Tools Appl, vol. 51, no. 1, pp. 133–162, 2011, doi: 10.1007/s11042-010-0620-1.

H. Farid, “Exposing Digital Forgeries from JPEG Ghosts,” IEEE Transactions on Information Forensics and Security, vol. 4, no. 1, pp. 154–160, Mar. 2009, doi: 10.1109/TIFS.2008.2012215.

N. K. Gill, R. Garg, and E. A. Doegar, “A Review Paper on Digital Image Forgery Detection Techniques,” in 8th International Conference on Computing, Communication and Networking Technologies, Delhi: IEEE, 2017. doi: 10.1109/ICCCNT.2017.8203904.

N. D. Arizona, M. A. Nugroho, A. R. Syujak, R. K. Saputra, and I. Sulistyowati, “Metadata Forensic Analysis as Support for Digital Investigation Process by Utilizing Metadata-Extractor,” Journal of Intelligent Software Systems, vol. 3, no. 2, pp. 27–31, Dec. 2024, doi: 10.26798/jiss.v3i2.1503.

N. A. N. Azhan, R. A. Ikuesan, S. A. Razak, and V. R. Kebande, “Error Level Analysis Technique for Identifying JPEG Block Unique Signature for Digital Forensic Analysis,” Electronics (Basel), vol. 11, no. 9, 2022, doi: 10.3390/electronics11091468.

M. Kharrazi, H. T. Sencar, and N. Memon, “BLIND SOURCE CAMERA IDENTIFICATION,” in 2004 International Conference on Image Processing, Singapore: IEEE, 2004, pp. 709–712. doi: 10.1109/ICIP.2004.1418853.

A. K. Boyat and B. K. Joshi, “A Review Paper : Noise Models in Digital Image Processing,” Signal Image Process, vol. 6, no. 2, pp. 63–75, Apr. 2015, doi: 10.5121/sipij.2015.6206.

J. Lukáš, J. Fridrich, and M. Goljan, “Detecting digital image forgeries using sensor pattern noise,” in Proc.SPIE, Feb. 2006, p. 60720Y. doi: 10.1117/12.640109.

J. Lukáš, J. Fridrich, and M. Goljan, “Digital Camera Identification from Sensor Pattern Noise,” IEEE Transactions on Information Forensics and Security, vol. 1, no. 2, pp. 205–214, Jun. 2006, doi: 10.1109/TIFS.2006.873602.

A. Piva, “An Overview on Image Forensics,” Int Sch Res Notices, vol. 2013, no. 1, p. 496701, Jan. 2013, doi: 10.1155/2013/496701.

A. Bharati et al., “Beyond Pixels: Image Provenance Analysis Leveraging Metadata,” in 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), 2019, pp. 1692–1702. doi: 10.1109/WACV.2019.00185.

N. Yu, L. Davis, and M. Fritz, “Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints,” Aug. 2019. doi: 10.48550/arXiv.1811.08180.

H. Bisri and M. I. Marzuki, “Forensik Citra Digital Menggunakan Metode Error Level Analysis, Clone Detection dan Exif Untuk Deteksi Keaslian Gambar,” G-Tech: Jurnal Teknologi Terapan, vol. 7, no. 2, pp. 586–595, Mar. 2023, doi: 10.33379/gtech.v7i2.2363.

D. Baracchi, D. Shullani, M. Iuliani, and A. Piva, “FloreView: An Image and Video Dataset for Forensic Analysis,” IEEE Access, vol. 11, pp. 109267–109282, Oct. 2023, doi: 10.1109/ACCESS.2023.3321991.

N. Soni, “Forensic Value of Exif Data: An Analytical Evaluation of Metadata Integrity across Image Transfer Methods,” Perspectives in Legal and Forensic Sciences, vol. 2, no. 2, 2025, doi: 10.70322/plfs.2025.10006.

M. Subli, M. M. Efendi, and Salman, “PERBANDINGAN HASIL ANALISA FOTO HOAX MENGGUNAKAN METODE EXIF/METADATA, REVERSE IMAGE DAN FORENSICS,” Jurnal Teknik Informatika dan Sistem Informasi, vol. 9, no. 1, pp. 798–811, May 2022, doi: 10.35957/jatisi.v9i1.1578.

S. Raghavan, “Digital forensic research: current state of the art,” CSI Transactions on ICT, vol. 1, no. 1, pp. 91–114, 2013, doi: 10.1007/s40012-012-0008-7.

T. Gloe, M. Kirchner, A. Winkler, and R. Böhme, “Can we trust digital image forensics?,” in Proceedings of the 15th ACM International Conference on Multimedia, in MM ’07. New York, NY, USA: Association for Computing Machinery, 2007, pp. 78–86. doi: 10.1145/1291233.1291252.

M. Anugraha, R. P. Kristianto, and A. Hartanto, “Forensic Metadata Analysis in Detecting Digital Image Manipulation,” Journal of Science and Computers, vol. 9, no. 2, pp. 56–61, Aug. 2025, doi: 10.61179/infact.v9i02.754.

T. S. Gunawan, S. A. M. Hanafiah, M. Kartiwi, N. Ismail, N. F. Za’bah, and A. N. Nordin, “Development of Photo Forensics Algorithm by Detecting Photoshop Manipulation Using Error Level Analysis,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 7, no. 1, pp. 131–137, 2017, doi: 10.11591/ijeecs.v7.i1.pp131-137.

T. Van Lanh, K.-S. Chong, S. Emmanuel, and M. S. Kankanhalli, “A Survey on Digital Camera Image Forensic Methods,” in 2007 IEEE International Conference on Multimedia and Expo, 2007, pp. 16–19. doi: 10.1109/ICME.2007.4284575.

Published
2025-12-18
Abstract views: 0 times
Download PDF: 0 times
How to Cite
Ferdiansyah, F., Deazwara, M. R., Billanivo, R., Ardiansyah, M., & Ilham, I. (2025). Forensic Analysis of AI-Generated Image Alterations Using Metadata Evaluation, ELA, and Noise Pattern Analysis. Journal of Information Systems and Informatics, 7(4), 4014-4035. https://doi.org/10.63158/journalisi.v7i4.1362
Issue
Vol 7 No 4 (2025): December
Section
Articles

Copyright (c) 2025 Journal of Information Systems and Informatics

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

  1. I certify that I have read, understand and agreed to the Journal of Information Systems and Informatics (Journal-ISI) submission guidelines, policies and submission declaration. Submission already using the provided template.
  2. I certify that all authors have approved the publication of this and there is no conflict of interest.
  3. I confirm that the manuscript is the authors' original work and the manuscript has not received prior publication and is not under consideration for publication elsewhere and has not been previously published.
  4. I confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
  5. I confirm that the paper now submitted is not copied or plagiarized version of some other published work.
  6. I declare that I shall not submit the paper for publication in any other Journal or Magazine till the decision is made by journal editors.
  7. If the paper is finally accepted by the journal for publication, I confirm that I will either publish the paper immediately or withdraw it according to withdrawal policies
  8. I Agree that the paper published by this journal, I transfer copyright or assign exclusive rights to the publisher (including commercial rights)