%0 Journal Article %T Surveillance Face Anti-spoofing %A Hao Fang %A Ajian Liu %A Jun Wan %A Sergio Escalera %A Chenxu Zhao %A Xu Zhang %A Stan Z Li %A Zhen Lei %J IEEE Transactions on Information Forensics and Security %D 2024 %V 19 %F Hao Fang2024 %O HUPBA;MILAB %O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3869), last updated on Fri, 14 Jun 2024 16:17:06 +0200 %X Face Anti-spoofing (FAS) is essential to secure face recognition systems from various physical attacks. However, recent research generally focuses on short-distance applications (i.e., phone unlocking) while lacking consideration of long-distance scenes (i.e., surveillance security checks). In order to promote relevant research and fill this gap in the community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask) dataset captured under 40 surveillance scenes, which has 101 subjects from different age groups with 232 3D attacks (high-fidelity masks), 200 2D attacks (posters, portraits, and screens), and 2 adversarial attacks. In this scene, low image resolution and noise interference are new challenges faced in surveillance FAS. Together with the SuHiFiMask dataset, we propose a Contrastive Quality-Invariance Learning (CQIL) network to alleviate the performance degradation caused by image quality from three aspects: (1) An Image Quality Variable module (IQV) is introduced to recover image information associated with discrimination by combining the super-resolution network. (2) Using generated sample pairs to simulate quality variance distributions to help contrastive learning strategies obtain robust feature representation under quality variation. (3) A Separate Quality Network (SQN) is designed to learn discriminative features independent of image quality. Finally, a large number of experiments verify the quality of the SuHiFiMask dataset and the superiority of the proposed CQIL. %U https://arxiv.org/abs/2301.00975 %U http://refbase.cvc.uab.es/files/FLW2023.pdf %P 1535-1546