Deepfake Content Analysis Using Error Level Analysis and Metadata
DOI:
https://doi.org/10.24076/intechnojournal.2026v8i1.2904Keywords:
Deepfake, Metadata, Error Level Analysis, Reality Defender, Digital Forensics, Platform XAbstract
Purpose: The spread of deepfakes on platform X threatens the integrity of digital information, but previous research has applied Metadata Analysis, Error Level Analysis (ELA), and Reality Defender separately, not yet as an integrated approach. This study applied Metadata Analysis and ELA to identify manipulation in deepfake images, as well as evaluate the effectiveness of Reality Defender in detecting deepfake content in images circulating on platform X as an application case study.
Methods/Study design/approach: Using a descriptive qualitative approach with digital forensic experiment methods, seven purposive selected image samples representing seven content characteristic scenarios (original, face-swap, GAN, full generative AI, anti-forensics, conventionally edited, and platform compressed), analyzed through three layered stages with tiered final classification criteria based on the cross-validated Reality Defender score threshold with ELA.
Result/Findings: Metadata is only informative before uploading, as X deletes EXIF uniformly post-upload. ELA remained effective in both conditions, showing localized intensity anomalies (close to 240-255 from 255) across deepfake samples. Reality Defender correctly classified six of the seven samples (85.7% accuracy, 100% in the deepfake category, 66.7% in the original category), with one false positive (64%) in the original, conventionally edited image.
Novelty/Originality/Value: This study integrated all three methods simultaneously and layered with explicit criteria, showing Metadata lost post-upload diagnostic value while ELA and Reality Defender remained the most reliable for content sourced from platform X.
References
[1] 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.
[2] R. Rafique, R. Gantassi, R. Amin, J. Frnda, A. Mustapha, and A. H. Alshehri, "Deep fake detection and classification using error-level analysis and deep learning," Sci. Rep., vol. 13, no. 1, pp. 1–13, 2023, doi: 10.1038/s41598-023-34629-3.
[3] Y. A. Fernandes and Y. Fatma, "Metode Deep Learning Dalam Teknologi Deepfake: Systematic Literature Review," JATI (Jurnal Mhs. Tek. Inform.), vol. 9, no. 2, pp. 3403–3410, 2025, doi: 10.36040/jati.v9i2.12987.
[4] D. Waringgi and S. Setiasih, "Business Competition Management in the Deepfake and Synthetic Media Era: Corporate Identity Verification as a Strategy to Mitigate Market Disinformation," J. Ekon. Balanc., vol. 21, no. 2, pp. 296–307, Dec. 2025, doi: 10.26618/FT7SDD96.
[5] Fortinet, "What Is Deepfake AI Endangering Your Cybersecurity Fortinet," 2025, Accessed: Apr. 19, 2026. [Online]. Available: https://www.fortinet.com/resources/cyberglossary/deepfake
[6] N. Halimah and F. Fachri, "Analisis Bukti Digital Twitter Web Menggunakan Live Forensic Pada Kasus Cyberbullying," JATI (Jurnal Mhs. Tek. Inform.), vol. 9, no. 1, pp. 1005–1010, 2024, doi: 10.36040/jati.v9i1.12554.
[7] L. D. V. Anggreni, I. G. A. A. M. Aristamy, K. Laksmi, Maswari, M. L. Radhitya, and I P. A. E. D. Udayana, "Sentiment Analysis of Public Opinion on the Impact of Deepfake Technology Using the Naive Bayes Method on Platform X," vol. 2, no. August, pp. 174–183, 2022, [Online]. Available: http://eprosiding.idbbali.ac.id/index.php/imade
[8] S. Singh, "Twitter (X) Users Statistics 2026 - Latest Global Data," Demandsage. Accessed: Apr. 06, 2026. [Online]. Available: https://www.demandsage.com/twitter-statistics/
[9] F. W. Giffary, "Penggunaan Metode Multilayer Perceptron untuk Identifikasi Sexual Harrassment Pada Media Sosial X (Twitter)," 2025, Accessed: Apr. 29, 2026. [Online]. Available: https://dspace.uii.ac.id/handle/123456789/59494
[10] A. A. Khan et al., "Cybersecurity, Digital Forensics, and the IoT for Deepfake Investigation on Social Media Platforms: A Review," Human-centric Comput. Inf. Sci., vol. 15, pp. 1–21, 2025, doi: 10.22967/HCIS.2025.15.038.
[11] R. N. Dasmen, M. R. Pratama, H. Yasir, and A. Budiman, "Analisis Forensik Digital Pada Kasus Cyberbullying Dengan Metode National Institute of Standard and Technology Sp 800-86," J. Ilm. Inform., vol. 12, no. 01, pp. 68–73, 2024, doi: 10.33884/jif.v12i01.8344.
[12] M. A. Kustian, "Analisis Forensik Penggunaan Fungsi Hash Dalam Menentukan Keaslian Video, Metadata Image Dan Magic Number File," J. Sains, Nalar, dan Apl. Teknol. Inf., vol. 2, no. 2, pp. 70–76, 2023, doi: 10.20885/snati.v2i2.21.
[13] Z. J. Syafar, Y. Salim, and A. R. Manga, "Analisis Penerapan Metode Exif Metadata Dan Metode Error Level Analysis Untuk Pengolahan Forensic Digital," LINIER Lit. Inform. dan Komput., vol. 2, no. 1, pp. 129–135, 2025, doi: 10.33096/linier.v2i1.2795.
[14] T. Oorloff et al., "AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection," Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 27092–27102, Jun. 2024, doi: 10.1109/CVPR52733.2024.02559.
[15] L. H. Liang, "Reality Defender brings web-based deepfake protection to enterprise | Biometric Update," Biometric Update.com. Accessed: May 12, 2026. [Online]. Available: https://www.biometricupdate.com/202511/reality-defender-brings-web-based-deepfake-protection-to-enterprise#respond
[16] K. R. Ahmed et al., "Enhanced Detection of GAN-Generated Image Forgeries Using Error Level Analysis and Deep Learning Models," IET Image Process., vol. 20, no. 1, p. e70345, Jan. 2026, doi: 10.1049/ipr2.70345.
[17] H. Bisri and M. I. Marzuki, "Forensik Citra Digital Menggunakan Metode Error Level Analysis, Clone Detection dan Exif Untuk Deteksi Keaslian Gambar," G-Tech J. Teknol. Terap., vol. 7, no. 2, pp. 586–595, Mar. 2023, doi: 10.33379/gtech.v7i2.2363.
[18] F. Ferdiansyah, M. R. A. Deazwara, R. R. Billanivo, M. Ardiansyah, and I. Ilham, "Forensic Analysis of AI-Generated Image Alterations Using Metadata Evaluation, ELA, and Noise Pattern Analysis," J. Inf. Syst. Informatics, vol. 7, no. 4, pp. 4014–4035, Dec. 2025, doi: 10.63158/journalisi.v7i4.1362.
[19] I. K. Khairullah, A. Yusa, A. D. Hartanto, Hartatik, and Kusnawi, "Deteksi Citra Digital Menggunakan Algoritma Cnn Dengan Model Normalisasi Rgb," Intechno J. (Information Technology Journal), vol. 2, no. 2, pp. 56–61, 2020, doi: 10.24076/intechnojournal.2020v2i2.1545.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Intechno Journal : Information Technology Journal
This work is licensed under a Creative Commons Attribution 4.0 International License.
