Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection
IEEE Transactions on Dependable and Secure Computing · 2025-11 · 22 (6) · 7010-7024
DOI: 10.1109/tdsc.2025.3592230 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Dependable and Secure Computing, 2025-11. Verfasst von Delong Zhu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 89 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Face-swapping DeepFakes have become an escalating societal concern, attracting increasing attention in recent years. To counter this, we investigate a new proactive defense framework to prevent individuals from being victimized in DeepFake videos. The core idea of this framework is to contaminate the inputs of DeepFake models by disrupting face detectors, based on the observation that face detectors are commonly used to automatically extract victim faces in most DeepFake techniques. Once the face detectors malfunction, the faces will not be correctly extracted, thereby impairing the training or synthesis stages of DeepFake models. To achieve this, we describe a strategy named FacePoison, which fools face detectors by adding dedicated adversarial perturbations to video frames. Building upon this, we introduce VideoFacePoison, an extended strategy that can efficiently propagate FacePoison across video frames instead of applying it individually to each frame, thus significantly reducing the computational overhead while retaining favorable attack performance. This framework is validated on five face detectors, and extensive experiments against eleven different DeepFake models demonstrate the effectiveness of disrupting face detectors to hinder DeepFake generation.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong Province
- China Postdoctoral Science Foundation
- Sanya Science and Technology Special Fund
- Basic and Applied Basic Research Foundation of Guangdong Province
- Shenzhen Science and Technology Program
Zitieren
APA
Zhu, D., Li, Y., Wu, B., Zhou, J., Wang, Z., & Lyu, S. (2025). Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection. IEEE Transactions on Dependable and Secure Computing, 22(6), 7010-7024. https://doi.org/10.1109/tdsc.2025.3592230
Vancouver
Zhu D, Li Y, Wu B, Zhou J, Wang Z, Lyu S. Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection. IEEE Transactions on Dependable and Secure Computing. 2025;22(6):7010-7024. doi:10.1109/tdsc.2025.3592230
BibTeX
@article{Zhu2025,
author = {Zhu, Delong and Li, Yuezun and Wu, Baoyuan and Zhou, Jiaran and Wang, Zhibo and Lyu, Siwei},
title = {Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection},
journal = {IEEE Transactions on Dependable and Secure Computing},
year = {2025},
volume = {22},
number = {6},
pages = {7010--7024},
doi = {10.1109/tdsc.2025.3592230}
}
EUVIMED