Application of Digital Image Processing in a Deepfake Detection Network

• Lucas Migliorin da Rosa State University of Amazonas
• Carlos Mauricio Serodio Figueiredo State University of Amazonas

DOI: https://doi.org/10.5753/eniac.2023.234266

Abstract

The evolution of Generative Adversarial Networks (GANs) opens up a range of possibilities for malicious users to leverage this technology in order to extract information from other users and spoof their identities. Tools such as DeepFaceLab is an example of the use of these networks to create increasingly realistic Deepfakes, which makes it easier and easier to change people's faces in images or videos. The present work presents an evolution of models for detecting deepfakes through the application of digital image processing techniques and the evolution of literature models applying more current convolutional backbones. Such models are evaluated on datasets from the literature such as the Deepfake Detection Challenge and Faceforensics++.

References

Abbas, G., Humayoun, S. R., AlTarawneh, R., and Ebert, A. (2018). Simple shape-based touch behavioral biometrics authentication for smart mobiles. In Proceedings of the 2018 International Conference on Advanced Visual Interfaces, pages 1–3.

Brian Dolhansky, Joanna Bitton, B. P. J. L. R. H. M. W. C. C. F. (2020). The deepfake detection challenge dataset.

Coccomini, D. A., Messina, N., Gennaro, C., and Falchi, F. (2022). Combining efficientnet and vision transformers for video deepfake detection. In Image Analysis and Processing–ICIAP 2022: 21st International Conference, Lecce, Italy, May 23–27, 2022, Proceedings, Part III, pages 219–229. Springer.

Gonzalez, R. C. and Woods, R. E. (2009). Processamento Digital de Imagens, volume 3. Person.

Guarnera, L., Giudice, O., and Battiato, S. (2020). Deepfake detection by analyzing convolutional traces. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pages 666–667.

Ismail, A., Elpeltagy, M., Zaki, M. S., and Eldahshan, K. (2021). A new deep learning-based methodology for video deepfake detection using XGBoost. Sensors, 21(16):5413.

Lewis, J. K., Toubal, I. E., Chen, H., Sandesera, V., Lomnitz, M., Hampel-Arias, Z., Prasad, C., and Palaniappan, K. (2020). Deepfake video detection based on spatial, spectral, and temporal inconsistencies using multimodal deep learning. In 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), pages 1–9. IEEE.

Perov, I., Gao, D., Chervoniy, N., Liu, K., Marangonda, S., Umé, C., Dpfks, M., Facenheim, C. S., RP, L., Jiang, J., Zhang, S., Wu, P., Zhou, B., and Zhang, W. (2020). Deepfacelab: Integrated, flexible and extensible face-swapping framework.

Rössler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., and Nießner, M. (2019). Faceforensics++: Learning to detect manipulated facial images. CoRR, abs/1901.08971.

Tan, M. and Le, Q. V. (2021). Efficientnetv2: Smaller models and faster training. CoRR, abs/2104.00298.

Zhang, K., Zhang, Z., Li, Z., and Qiao, Y. (2016). Joint face detection and alignment using multi-task cascaded convolutional networks. CoRR, abs/1604.02878.

Zhao, H., Zhou, W., Chen, D., Wei, T., Zhang, W., and Yu, N. (2021). Multi-attentional deepfake detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2185–2194.