Generalizable Method for Face Anti-Spoofing with Semi-Supervised Learning

Face anti-spoofing has drawn a lot of attention due to the high security requirements in biometric authentication systems. Bringing face biometric to commercial hardware became mostly dependent on developing reliable methods for detecting fake login sessions without specialized sensors. Current CNN-...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-06
Main Authors: Sergievskiy, Nikolay, Vlasov, Roman, Trusov, Roman
Format: Article
Language:English
Subjects:
Access control
Classification
Datasets
Semi-supervised learning
Spoofing
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Face anti-spoofing has drawn a lot of attention due to the high security requirements in biometric authentication systems. Bringing face biometric to commercial hardware became mostly dependent on developing reliable methods for detecting fake login sessions without specialized sensors. Current CNN-based method perform well on the domains they were trained for, but often show poor generalization on previously unseen datasets. In this paper we describe a method for utilizing unsupervised pretraining for improving performance across multiple datasets without any adaptation, introduce the Entry Antispoofing Dataset for supervised fine-tuning, and propose a multi-class auxiliary classification layer for augmenting the binary classification task of detecting spoofing attempts with explicit interpretable signals. We demonstrate the efficiency of our model by achieving state-of-the-art results on cross-dataset testing on MSU-MFSD, Replay-Attack, and OULU-NPU datasets.
ISSN:2331-8422