OPTIMIZING CNN PERFORMANCE FOR AI-GENERATED IMAGE CLASSIFICATION: A COMPARATIVE STUDY OF ARCHITECTURES AND OPTIMIZERS USING K-FOLD CROSS-VALIDATION

Fransiscus Rolanda Malau

doi:10.24252/instek.v9i2.54193

Fransiscus Rolanda Malau Universitas Nusa Mandiri
(ID)

DOI: https://doi.org/10.24252/instek.v9i2.54193

Keywords: Convolutional Neural Network, AI-Generated Images, Image Classification, Optimization Algorithms, Attention Mechanisms

Abstract

This study investigates CNN optimization for classifying AI-generated images. Using the CIFAKE dataset (60,000 real and 60,000 AI-generated images), we evaluated four CNN configurations with varying complexity and four optimization algorithms through 5-fold cross-validation. Our findings show Configuration 4 (4 Conv, 2 MaxPool) with Adam optimizer achieved the highest validation accuracy (0.8368±0.0135). Adam demonstrated consistent performance across architectures, while SGD showed strong but variable results improving with model complexity. Adagrad and Adadelta consistently underperformed. The final model achieved 85.28% test accuracy with balanced precision (0.8531) and recall (0.8528). Results indicate more complex architectures combined with adaptive optimizers like Adam provide superior performance for AI-generated image classification, with the balance between model complexity and optimizer selection being crucial. The consistent performance across real and fake categories demonstrates this approach's robustness for deepfake detection applications.

Downloads

Download data is not yet available.

References

Ali MEA, Kumar D. 2022. The Impact of Optimization Algorithms on The Performance of Face Recognition Neural Networks. Journal of Advanced Engineering and Computing. 6(4):248.

Althnian A, AlSaeed D, Al-Baity H, Samha A, Dris AB, Alzakari N, Abou Elwafa A, Kurdi H. 2021. Impact of Dataset Size on Classification Performance: An Empirical Evaluation in the Medical Domain. Applied Sciences. 11(2):796.

Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Santamaría J, Fadhel MA, Al-Amidie M, Farhan L. 2021. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data. 8(1):53.

Bera S, Shrivastava VK. 2020. Analysis of various optimizers on deep convolutional neural network model in the application of hyperspectral remote sensing image classification. International Journal of Remote Sensing. 41(7):2664-2683.

Bonettini A, Bestagini V, Milani S, Tubaro S. 2020. On the use of Benford's law to detect GAN-generated images. Proceedings of IEEE International Conference on Pattern Recognition. January 2020. Milan: IEEE. pp 5495-5500.

Chen F, Tsou JY. 2022. Assessing the effects of convolutional neural network architectural factors on model performance for remote sensing image classification: An in-depth investigation. International Journal of Applied Earth Observation and Geoinformation. 112:102865.

Choi D, Shallue CJ, Nado Z, Lee J, Maddison CJ, Dahl GE. 2020. On Empirical Comparisons of Optimizers for Deep Learning. arXiv preprint arXiv:1910.05446.

Croce F, Noroozi M, Scimeca M, Birchfield S. 2022. CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images. IEEE Access. 10:127154-127164.

Das S, Seferbekov S, Datta A, Islam MS, Amin MR. 2021. Towards Solving the DeepFake Problem: An Analysis on Improving DeepFake Detection using Dynamic Face Augmentation. arXiv preprint arXiv:2102.09603.

Du X, Sun Y, Song Y, Sun H, Yang L. 2023. A Comparative Study of Different CNN Models and Transfer Learning Effect for Underwater Object Classification in Side-Scan Sonar Images. Remote Sensing. 15(3):593.

Guera D, Delp EJ. 2018. Deepfake Video Detection Using Recurrent Neural Networks. Proceedings of the 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). November 2018. Auckland: IEEE. pp 1-6.

Hao H, Parmar D, Sitaram S, Raja S, Yamasaki T, Aizawa K. 2022. Deepfake Detection Using Multiple Data Modalities. In: Rathgeb C, Tolosana R, Vera-Rodriguez R, Busch C (eds). Handbook of Digital Face Manipulation and Detection. Cham: Springer International Publishing. pp 235-254.

Hassan E, Shams MY, Hikal NA, Elmougy S. 2023. The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study. Multimedia Tools and Applications. 82(11):16591-16633.

Hicks SA, Strümke I, Thambawita V, Hammou M, Riegler MA, Halvorsen P, Parasa S. 2022. On evaluation metrics for medical applications of artificial intelligence. Scientific Reports. 12(1):5979.

Jaiswal A, Sabharwal S, Javed AR, Singh R. 2022. AI-generated synthetic face detection: A pattern analysis-based approach. Computers & Electrical Engineering. 104:108383.

Kohavi R. 1995. A study of cross-validation and bootstrap for accuracy estimation and model selection. Proceedings of the 14th International Joint Conference on Artificial Intelligence (IJCAI). August 1995. Montreal: Morgan Kaufmann. pp 1137-1143.

LeCun Y, Bengio Y, Hinton G. 2015. Deep learning. Nature. 521(7553):436-444.