Saved in:
Bibliographic Details
Main Authors: Chen, Jiawei, Yang, Xiao, Yin, Heng, Ma, Mingzhi, Chen, Bihui, Peng, Jianteng, Guo, Yandong, Yin, Zhaoxia, Su, Hang
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2308.02116
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929326900903936
author Chen, Jiawei
Yang, Xiao
Yin, Heng
Ma, Mingzhi
Chen, Bihui
Peng, Jianteng
Guo, Yandong
Yin, Zhaoxia
Su, Hang
author_facet Chen, Jiawei
Yang, Xiao
Yin, Heng
Ma, Mingzhi
Chen, Bihui
Peng, Jianteng
Guo, Yandong
Yin, Zhaoxia
Su, Hang
contents Ensuring the reliability of face recognition systems against presentation attacks necessitates the deployment of face anti-spoofing techniques. Despite considerable advancements in this domain, the ability of even the most state-of-the-art methods to defend against adversarial examples remains elusive. While several adversarial defense strategies have been proposed, they typically suffer from constrained practicability due to inevitable trade-offs between universality, effectiveness, and efficiency. To overcome these challenges, we thoroughly delve into the coupled relationship between adversarial detection and face anti-spoofing. Based on this, we propose a robust face anti-spoofing framework, namely AdvFAS, that leverages two coupled scores to accurately distinguish between correctly detected and wrongly detected face images. Extensive experiments demonstrate the effectiveness of our framework in a variety of settings, including different attacks, datasets, and backbones, meanwhile enjoying high accuracy on clean examples. Moreover, we successfully apply the proposed method to detect real-world adversarial examples.
format Preprint
id arxiv_https___arxiv_org_abs_2308_02116
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle AdvFAS: A robust face anti-spoofing framework against adversarial examples
Chen, Jiawei
Yang, Xiao
Yin, Heng
Ma, Mingzhi
Chen, Bihui
Peng, Jianteng
Guo, Yandong
Yin, Zhaoxia
Su, Hang
Computer Vision and Pattern Recognition
Artificial Intelligence
Ensuring the reliability of face recognition systems against presentation attacks necessitates the deployment of face anti-spoofing techniques. Despite considerable advancements in this domain, the ability of even the most state-of-the-art methods to defend against adversarial examples remains elusive. While several adversarial defense strategies have been proposed, they typically suffer from constrained practicability due to inevitable trade-offs between universality, effectiveness, and efficiency. To overcome these challenges, we thoroughly delve into the coupled relationship between adversarial detection and face anti-spoofing. Based on this, we propose a robust face anti-spoofing framework, namely AdvFAS, that leverages two coupled scores to accurately distinguish between correctly detected and wrongly detected face images. Extensive experiments demonstrate the effectiveness of our framework in a variety of settings, including different attacks, datasets, and backbones, meanwhile enjoying high accuracy on clean examples. Moreover, we successfully apply the proposed method to detect real-world adversarial examples.
title AdvFAS: A robust face anti-spoofing framework against adversarial examples
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2308.02116