SCPAD: An approach to explore optical characteristics for robust static presentation attack detection

Presentation attack detection approaches have achieved great progress on various attack types while adversarial learning technology has become a new threat to these approaches. Now few works are devoted to developing a robust detection method for both physical spoofing faces and digital adversarial...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications 2024-02, Vol.83 (5), p.14503-14520
Main Authors: Dang, Chen, Xia, Zhaoqiang, Dai, Jing, Gao, Jie, Li, Lei, Feng, Xiaoyi
Format: Article
Language:English
Subjects:
Algorithms
Biometrics
Color texture
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Digital imaging
Facial recognition technology
Multimedia
Multimedia Information Systems
Neural networks
Optical properties
Robustness
Special Purpose and Application-Based Systems
Spoofing
Track 6: Computer Vision for Multimedia Applications
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Presentation attack detection approaches have achieved great progress on various attack types while adversarial learning technology has become a new threat to these approaches. Now few works are devoted to developing a robust detection method for both physical spoofing faces and digital adversarial faces. In this paper, we find that fake face images from printed photos and replayed videos have a different optical characteristic from the real ones, and the adversarial samples generated by various attacking methods retain this characteristic. By exploring this characteristic, we propose the Spectral Characteristic Presentation Attack Detection (SCPAD), a new approach that detects presentation attacks by reconstructing the color space of input images, which also performs well on adversarial samples. More specifically, a new HSCbb color space is manually constructed by studying the difference in albedo intensity between real faces and fake faces. Then the difference between real and spoofing faces can be effectively magnified and modeled by color texture features with the shallow convolutional network. The experimental results show that our proposed method consistently outperforms the state-of-the-art methods on adversarial faces and also achieves competitive performance on fake faces.
ISSN:1573-7721
1380-7501
1573-7721
DOI:10.1007/s11042-023-15870-4