EUVIMEDEUVIMED entdecken
Crossref

AI-GENERATED IMAGE DETECTION USING SIXCHANNEL MULTI FORENSIC CONVOLUTION NUERAL NETWORKS (CNN) FUSION

Nazirah Abd Hamid, Shaifol Ziqri Zainurin, Siti Dhalila Mohd Satar, Norhidayah Muhammad, Mohd Fadzil Abdul Kadir, Muhammad Syakir Razmin, Muhammad Daniel Mohd, Shaiful Azhari, Nur Wasilah Jamlih

The International journal of Multimedia & Its Applications · 28.06.2026 · 18 (3) · 01-14

DOI: 10.5121/ijma.2026.18301 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The International journal of Multimedia & Its Applications, online erschienen am 28.06.2026. Verfasst von Nazirah Abd Hamid und 8 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern generative artificial intelligence (AI) can generate highly realistic synthetic images, making current detection system that rely on standard RGB input tends to miss the underlying generative artifacts. This research develops a framework based on Convolutional Neural Network (CNN) that aims to distinguish between original digital images and artificial media. This work proposes a multi-modal, six channel forensic fusion architectures that combines standard visual data with advanced digital forensic features to reveal hidden generative artifacts. The proposed method utilizes three specific forensic layers, Error Level Analysis (ELA) to find inconsistencies in image compression, Fast Fourier Transform (FFT) to detect abnormal frequency patterns, and Laplacian High-Pass Filtering (HPF) to extract high-frequency background noise as Photo Response Non-Uniformity (PRNU) alternative. The first layer of three baseline models which are MobileNetV3-small, MobileNetV2, and ResNet50 were modified to directly process the combined six-channel input. The framework was trained, validated and tested based on balanced subset of 16,000 images from the CIFake dataset. The performance of all models was measured using accuracy, precision, False Acceptance Rate (FAR), False Rejection Rate (FRR), F1-score, and overall computational cost. Implementing these forensic features significantly improved the accuracy of lightweight models. As a result, MobileNetV2 accuracy jumped from 77.62% using only standard RGB to 94.94% with the new six channel input, while MobileNetV3-small achieved the highest overall test accuracy of 95.69%. This multi feature approach can be used in real-world applications like digital forensics, automated content moderation, and cybersecurity, where verifying image authenticity is critical. Overall, the findings indicate that combining traditional method with forensic features with CNN-based model can improve detection accuracy, even with lightweight models

Zitieren

APA

Hamid, N. A., Zainurin, S. Z., Satar, S. D. M., Muhammad, N., Kadir, M. F. A., Razmin, M. S., Mohd, M. D., Azhari, S., & Jamlih, N. W. (2026). AI-GENERATED IMAGE DETECTION USING SIXCHANNEL MULTI FORENSIC CONVOLUTION NUERAL NETWORKS (CNN) FUSION. The International journal of Multimedia & Its Applications, 18(3), 01-14. https://doi.org/10.5121/ijma.2026.18301

Vancouver

Hamid NA, Zainurin SZ, Satar SDM, Muhammad N, Kadir MFA, Razmin MS, et al. AI-GENERATED IMAGE DETECTION USING SIXCHANNEL MULTI FORENSIC CONVOLUTION NUERAL NETWORKS (CNN) FUSION. The International journal of Multimedia & Its Applications. 2026;18(3):01-14. doi:10.5121/ijma.2026.18301

BibTeX
@article{Hamid2026,
  author = {Hamid, Nazirah Abd and Zainurin, Shaifol Ziqri and Satar, Siti Dhalila Mohd and Muhammad, Norhidayah and Kadir, Mohd Fadzil Abdul and Razmin, Muhammad Syakir and Mohd, Muhammad Daniel and Azhari, Shaiful and Jamlih, Nur Wasilah},
  title = {AI-GENERATED IMAGE DETECTION USING SIXCHANNEL MULTI FORENSIC CONVOLUTION NUERAL NETWORKS (CNN) FUSION},
  journal = {The International journal of Multimedia & Its Applications},
  year = {2026},
  volume = {18},
  number = {3},
  pages = {01--14},
  doi = {10.5121/ijma.2026.18301}
}
Kostenlos starten →