A Dynamic Ensemble Selection of Deepfake Detectors Specialized for Individual Face Parts
-
Published:2023-09-18
Issue:18
Volume:12
Page:3932
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Kawabe Akihisa1, Haga Ryuto2, Tomioka Yoichi2ORCID, Shin Jungpil2ORCID, Okuyama Yuichi2
Affiliation:
1. Graduate School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, Japan 2. School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, Japan
Abstract
The development of deepfake technology, based on deep learning, has made it easier to create images of fake human faces that are indistinguishable from the real thing. Many deepfake methods and programs are publicly available and can be used maliciously, for example, by creating fake social media accounts with images of non-existent human faces. To prevent the misuse of such fake images, several deepfake detection methods have been proposed as a countermeasure and have proven capable of detecting deepfakes with high accuracy when the target deepfake model has been identified. However, the existing approaches are not robust to partial editing and/or occlusion caused by masks, glasses, or manual editing, all of which can lead to an unacceptable drop in accuracy. In this paper, we propose a novel deepfake detection approach based on a dynamic configuration of an ensemble model that consists of deepfake detectors. These deepfake detectors are based on convolutional neural networks (CNNs) and are specialized to detect deepfakes by focusing on individual parts of the face. We demonstrate that a dynamic selection of face parts and an ensemble of selected CNN models is effective at realizing highly accurate deepfake detection even from partly edited and occluded images.
Funder
JSPS KAKENHI SEI Group CSR Foundation
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference36 articles.
1. Wang, R., Huang, Z., Chen, Z., Liu, L., Chen, J., and Wang, L. (2022). Anti-Forgery: Towards a Stealthy and Robust DeepFake Disruption Attack via Adversarial Perceptual-aware Perturbations. arXiv. 2. Karras, T., Aila, T., Laine, S., and Lehtinen, J. (2017). Progressive growing of gans for improved quality, stability, and variation. arXiv. 3. Karras, T., Laine, S., and Aila, T. (2019, January 15–20). A style-based generator architecture for generative adversarial networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA. 4. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., and Aila, T. (2020, January 13–19). Analyzing and improving the image quality of stylegan. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA. 5. Liu, M., Ding, Y., Xia, M., Liu, X., Ding, E., Zuo, W., and Wen, S. (2019, January 15–20). Stgan: A unified selective transfer network for arbitrary image attribute editing. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.
|
|