Face Reconstruction-Based Generalized Deepfake Detection Model with Residual Outlook Attention
ACM Transactions on Multimedia Computing, Communications, and Applications · 30.04.2025 · 21 (4) · 1-19
DOI: 10.1145/3686162 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 12.03.2025. Verfasst von Zenan Shi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Jilin Province Science and Technology Development Plan Key R & D Project.
Abstract (Originalsprache)
With the continuous development of deep counterfeiting technology, the information security in our daily life is under serious threat. While existing face forgery detection methods exhibit impressive accuracy when applied to datasets such as FaceForensics++ and Celeb-DF, they falter significantly when confronted with out-of-domain scenarios. This causes specialization of learned representations to known forgery patterns presented in the training set, rendering it difficult to detect forgeries with unknown patterns. To address this challenge, we propose a novel end-to-end Face Reconstruction-Based Generalized Deepfake Detection (FRG2D) model with Residual Outlook Attention (ROA) , which emphasizes the robust visual representations of genuine faces and discerns the subtle differences between authentic and manipulated facial images. Our methodology entails reconstructing authentic face images using an encoder–decoder architecture based on U-net, facilitating a deeper understanding of disparities between genuine and manipulated facial images. Furthermore, we integrate the convolutional block attention module (CBAM) and channel attention block (CAB) to selectively focus the network’s attention on salient features within real face images. Furthermore, we employ ROA to guide the network’s focus towards precise features within manipulated facial images. Simultaneously, the computed reconstruction differences obtained through ROA serves as the ultimate representation fed into the classifier for face forgery detection. Both the reconstruction and classification learning processes are optimized end-to-end. Through extensive experimentation, our model demonstrated a substantial improvement in deepfake detection across unknown domains, while maintaining a high accuracy within the known domain.
Förderung
- National Natural Science Foundation of China
- Jilin Province Science and Technology Development Plan Key R & D Project
Zitieren
APA
Shi, Z., Liu, W., & Chen, H. (2025). Face Reconstruction-Based Generalized Deepfake Detection Model with Residual Outlook Attention. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(4), 1-19. https://doi.org/10.1145/3686162
Vancouver
Shi Z, Liu W, Chen H. Face Reconstruction-Based Generalized Deepfake Detection Model with Residual Outlook Attention. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(4):1-19. doi:10.1145/3686162
BibTeX
@article{Shi2025,
author = {Shi, Zenan and Liu, Wenyu and Chen, Haipeng},
title = {Face Reconstruction-Based Generalized Deepfake Detection Model with Residual Outlook Attention},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2025},
volume = {21},
number = {4},
pages = {1--19},
doi = {10.1145/3686162}
}
EUVIMED