Deepfake Detection: A Comparative Approach

• Julia Campanelli Granja Universidade Federal de São Carlos (UFSCar)
• Marcela Xavier Ribeiro Universidade Federal de São Carlos (UFSCar)

DOI: https://doi.org/10.5753/sbbd_estendido.2026.249936

Resumo

The rapid advancement of synthetic image generation techniques, such as Generative Adversarial Networks (GANs), has enabled the creation of realistic deepfakes, raising concerns regarding misinformation, privacy, and digital security. This work investigates automatic methods for detecting fake facial images, focusing on convolutional neural networks (CNNs) and classical techniques such as SVM and Random Forest. Experiments were conducted using a merged dataset composed of the Real and Fake Face Detection and Human Faces datasets, totaling 10,025 images. The results indicate that the tested methods achieve satisfactory performance, demonstrating the feasibility of using machine learning approaches for automatic deepfake detection. Performance and interpretability aspects are discussed, showing the superiority of CNNs in classifying fake images, achieving an average accuracy of 94.2% in the conducted tests.

Palavras-chave: image generation, deepfake, computer vision, machine learning

Referências

Ankolekar, A., Madappa, R., and Savakis, A. E. (2022). Can simpler be better? review of methods for the detection of gan-generated imagery. In Defense + Commercial Sensing.

Arora, T. and Soni, R. (2021). A review of techniques to detect the gan-generated fake images. In Generative Adversarial Networks for Image-to-Image Translation, pages 125–159. Elsevier.

Chauhan, R., Popli, R., and Kansal, I. (2023). A systematic review on fake image creation techniques. In 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom), pages 779–783. IEEE.

CIPLAb (2020). Real and fake face detection. [link]. Acesso em jul.2025.

Guarnera, L., Giudice, O., and Battiato, S. (2022). The face deepfake detection challenge. Journal of Imaging, 8(10):263.

Gupta, A. (2021). Human faces. [link]. Acesso em jul.2025.

Heidari, A., Jafari Navimipour, N., Dag, H., and Unal, M. (2024). Deepfake detection using deep learning methods: A systematic and comprehensive review. WIREs Data Mining and Knowledge Discovery, 14(2):e1520.

Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., and Aila, T. (2020). Analyzing and improving the quality of gans for image synthesis. Advances in Neural Information Processing Systems (NeurIPS), 33:8107–8118.

Khoo, B., Phan, R. C.-W., and Lim, C.-H. (2022). Deepfake attribution: On the source identification of artificially generated images. WIREs Data Mining and Knowledge Discovery, 12(3):e1438.

Malik, A., Usama, M., Ali, M., and Razzak, I. (2022). Deepfake detection for human face images and videos: A survey. IEEE Access, 10:18757–18775.

Perov, I., Gao, D., Chervoniy, N., Liu, K., Marangonda, S., Umé, C., Dpfks, M., Facenheim, C. S., RP, L., Jiang, J., et al. (2020). Deepfacelab: Integrated, flexible and extensible face-swapping framework. arXiv preprint arXiv:2005.05535.

TAVARES, C. D. M. (2024). Inteligência artificial e deepfakes: Desafios jurídicos e tecnológicos para a integridade do processo democrático. Revista Justiça Eleitoral em Debate, 14(1).