AI-Generated Image Detection Using Convolutional Neural Network (CNN) Algorithm

Muhamad Shadri; Anggi Hanafiah; Parthasarathy Velusamy

AI-Generated Image Detection Using Convolutional Neural Network (CNN) Algorithm

Authors

Muhamad Shadri

Islamic University of Riau

Author
Anggi Hanafiah

Islamic University of Riau

Author
Parthasarathy Velusamy

Karpagam Academy of Higher Education

Author

Keywords:

Image detection, AI-generated, Convolutional Neural Network, MobileNetV2, Image classification

Abstract

The detection of AI-generated images has become a critical challenge in ensuring the authenticity of visual content. This study aims to develop a classification system for AI-generated and non-AI-generated images using Convolutional Neural Network (CNN) models, including MobileNet, MobileNetV2, ResNet50, and a Custom CNN. The dataset comprises 16,000 images, evenly divided into AI-generated and non-AI generated categories. Before training, the dataset was split into 80% training, 10% validation, and 10% testing. Experiments utilized Adam and RMSprop optimizers with learning rates of 0.001 and 0.0001 across 50 and 100 epochs. Results indicate that MobileNetV2 with Adam, a 0.001 learning rate, and 100 epochs achieved the best performance, with 92.87% training accuracy and 88% testing accuracy. MobileNetV2 detected AI-generated images with a precision of 0.81, recall of 0.96, and an F1-score of 0.88, while non-AI-generated images had a precision of 0.95, recall of 0.77, and an F1-score of 0.85. These findings demonstrate that MobileNetV2 outperforms other models in both accuracy and efficiency. This highlights the significance of robust AI image detection models in ensuring the authenticity of digital content, contributing to the broader effort in combating AI-generated misinformation.

Downloads

Download data is not yet available.

References

Fajrin, F.A.; Sugiastuti, N.Y. The Ability of Indonesian Lawyers in Assisting the Development of Copyright Protection Law in Indonesia for Comic Books Whose Illustrations are Created with the Aid of Artificial Intelligence. JURNAL LEX PHAENOMENON 2024, 1, 74–93.

Yusuf, A. VIRAL Karya Fotografer Indonesia Juara di Eropa Dituduh Hasil AI, Warganet Miris Negara Penuduh. https://kalteng.tribunnews.com/2023/10/19/viral-karya-fotografer-indonesia-juara-di-eropa-dituduh-hasil-ai-warganet-miris-negara-penuduh

2023. Accessed on October 20, 2024.

Raharja, A.R.; Jayadi.; Pramudianto, A.; Muchsam, Y. Penerapan Algoritma Decision Tree dalam Klasifikasi Data “Framingham” Untuk Menunjukkan Risiko Seseorang Terkena Penyakit Jantung dalam 10 Tahun Mendatang. Technologia Journal 2024, 1.

Pujiono, S.; Astuti, R.; Basysyar, F.M. Implementasi Data Mining Untuk Menentukan Pola Penjualan Produk Menggunakan Algoritma K-Means Clustering. JATI (Jurnal Mahasiswa Teknik Informatika) 2024, 8, 615–620.

Joseph, V.R. Optimal ratio for data splitting. Statistical Analysis and Data Mining: The ASA Data Science Journal 2022, 15, 531–538.

Rizki, F.; Putra, M.P.K.; Assuja, M.A.; Ariany, F. Implementasi Deep Leraning Lenet Dengan Augmentasi Data Pada Identifikasi Anggrek. Jurnal Informatika dan Rekayasa Perangkat Lunak 2023, 4, 357–366.

Muhartini, S.; Sunyoto, A.; Muhammad, A.H. Implementasi Metode Deep Learning CNN Dalam Klasifikasi Tajong (Sarung) Samarinda. Jurnal SENOPATI: Sustainability, Ergonomics, Optimization, and Application of Industrial Engineering 2024, 6, 28–41.

Utomo, M.W.S.; Murti, H.W.; Sujatmoko, A.W.I.; Sari, A.P. DETEKSI SPAM EMAIL MENGGUNAKAN METODE LSTM (LONG SHORT TERM MEMORY). JATI (Jurnal Mahasiswa Teknik Informatika) 2024, 8, 11406–11411.

Bintang, Y.K.; Imaduddin, H. Pengembangan Model Deep learning untuk Deteksi Retinopati Diabetik Menggunakan Metode Transfer Learning. JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) 2024, 9, 1442–1455.

Fadhillah, I.R.; Al Haromainy, M.M.; Maulana, H. Implementasi Model Transfer Learning EfficientNet untuk Pendeteksian Bahasa Isyarat Indonesia (BISINDO) pada Perangkat Android. JATI (Jurnal Mahasiswa Teknik Informatika) 2024, 8, 7816–7822.

Agustina, A. KLASIFIKASI PENYAKIT TANAMAN PADI MENGGUNAKAN METODE CNN ARSITEKTUR DENSENET121 DAN AUGMENTASI DATA 2024, 8.

Syaharani, M.A.; Budianto, T.A.C.; Adam, R.I. KLASIFIKASI BUAH SEGAR DAN BUSUK MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN). JATI (Jurnal Mahasiswa Teknik Informatika) 2024, 8, 10823–10827.

Abel, S.; Pranidana, A.M.; Qasos, L.; Ula, M.; et al. Perbandingan Akurasi Metode Convolutional Neural Network (CNN) dan Sobel untuk Klasifikasi Buah Rambutan melalui Pengolahan Citra. In Proceedings of the Prosiding Seminar Nasional Teknologi dan Teknik Informatika (SENASTIKA), 2024, 1.

Khumaidi, A.; Nurpadilah, A. Klasifikasi Molting Kepiting Soka Menggunakan Algoritma Convolusional Neural Network. Komputa: Jurnal Ilmiah Komputer dan Informatika 2024, 13, 43–50.

Apendi, S.; Setianingsih, C.; Paryasto, M.W. Deteksi Bahasa Isyarat Sistem Isyarat Bahasa Indonesia Menggunakan Metode Single Shot Multibox Detector. eProceedings of Engineering 2023, 10.

Haksoro, E.I.S.; Setiawan, A. Pengenalan Jamur Yang Dapat Dikonsumsi Menggunakan Metode Transfer Learning Pada Convolutional Neural Network. Jurnal ELTIKOM 2021, 5, 81–91.

Fadlun, M.H.; Martanto, M.; Hayati, U. Klasifikasi Tumor Otak menggunakan Convolutional Neural Network dan Transfer Learning. Jurnal Informatika dan Rekayasa Perangkat Lunak 2024, 6, 289–295.

Prilianti, K.R.; Oktariyanto, V.V.; Setiawan, H. ORNAMENTAL PLANT IDENTIFICATION SYSTEM USING TRANSFER LEARNING ON CONVOLUTIONAL NEURAL NETWORK. Jurnal Teknik Informatika (Jutif) 2024, 5, 1015–1023.

Ae, N.H.; Zul, M.I.; et al. Aplikasi Penerjemah Bahasa Isyarat Indonesia menjadi Suara berbasis Android menggunakan Tensorflow. Jurnal Komputer Terapan 2021, 7, 74–83.

Firmansah, R.A.; Santoso, H.; Anwar, A. Transfer Learning Implementation on Image Recognition of Indonesian Traditional Houses. Jurnal Teknik Informatika (Jutif) 2023, 4, 1469–1478.

Maulana, S.A.; Batubara, S.H.; Pasaribu, Y.P.P.; Syahputra, H.; Ramadhani, F. DETEKSI BURUNG MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN) DENGAN MODEL ARSITEKTUR MOBILENETV2. JATI (Jurnal Mahasiswa Teknik Informatika) 2024, 8, 6108–6114.

Cover Image

Examples of AI-generated and non-AI images

Downloads

PDF

Published

2026-04-23

Issue

Vol. 1 No. 1 (2026): Volume 1, Issue 1

Section

Articles

How to Cite

[1]

M. Shadri, A. Hanafiah, and P. Velusamy, “AI-Generated Image Detection Using Convolutional Neural Network (CNN) Algorithm”, Artif. Intell. Lang. Models, vol. 1, no. 1, pp. 1–11, Apr. 2026, Accessed: Apr. 26, 2026. [Online]. Available: https://acspub.id/index.php/ailm/article/view/4

Download Citation

AI-Generated Image Detection Using Convolutional Neural Network (CNN) Algorithm

How to Cite

Similar Articles