Detect and Locate : Exposing Face Manipulation by Semantic- and Noise-level Telltales
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 1741-1756 |
Journal / Publication | IEEE Transactions on Information Forensics and Security |
Volume | 17 |
Online published | 28 Apr 2022 |
Publication status | Published - 2022 |
Link(s)
Abstract
The technological advancements of deep learning have enabled sophisticated face manipulation schemes, raising severe trust issues and security concerns in modern society. Generally speaking, detecting manipulated faces and locating the potentially altered regions are challenging tasks. Herein, we propose a conceptually simple but effective method to efficiently detect forged faces in an image while simultaneously locating the manipulated regions. The proposed scheme relies on a segmentation map that delivers meaningful high-level semantic information clues about the image. Furthermore, a noise map is estimated, playing a complementary role in capturing low-level clues and subsequently empowering decision-making. Finally, the features from these two modules are combined to distinguish fake faces. Extensive experiments show that the proposed model achieves state-of-the-art detection accuracy and remarkable localization performance.
Research Area(s)
- Data mining, Face forensics, face forgery detection, face manipulation localization, Faces, Feature extraction, Forgery, Location awareness, Semantics, Training
Citation Format(s)
Detect and Locate: Exposing Face Manipulation by Semantic- and Noise-level Telltales. / Kong, Chenqi; Chen, Baoliang; Li, Haoliang et al.
In: IEEE Transactions on Information Forensics and Security, Vol. 17, 2022, p. 1741-1756.
In: IEEE Transactions on Information Forensics and Security, Vol. 17, 2022, p. 1741-1756.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review