Federated Test-Time Adaptive Face Presentation Attack Detection with Dual-Phase Privacy Preservation

TL;DR

This paper introduces a privacy-preserving federated learning framework for face presentation attack detection that enhances model generalization across unseen attacks through test-time adaptation.

Contribution

It proposes a dual-phase privacy-preserving federated learning and test-time adaptation framework for face PAD, improving generalization without sharing private data.

Findings

Federated learning effectively aggregates knowledge from multiple sources.

Test-time entropy minimization improves detection accuracy on unseen attacks.

The framework maintains privacy while enhancing model robustness.

Abstract

Face presentation attack detection (fPAD) plays a critical role in the modern face recognition pipeline. The generalization ability of face presentation attack detection models to unseen attacks has become a key issue for real-world deployment, which can be improved when models are trained with face images from different input distributions and different types of spoof attacks. In reality, due to legal and privacy issues, training data (both real face images and spoof images) are not allowed to be directly shared between different data sources. In this paper, to circumvent this challenge, we propose a Federated Test-Time Adaptive Face Presentation Attack Detection with Dual-Phase Privacy Preservation framework, with the aim of enhancing the generalization ability of fPAD models in both training and testing phase while preserving data privacy. In the training phase, the proposed framework exploits the federated learning technique, which simultaneously takes advantage of rich fPAD information available at different data sources by aggregating model updates from them without accessing their private data. To further boost the generalization ability, in the testing phase, we explore test-time adaptation by minimizing the entropy of fPAD model prediction on the testing data, which alleviates the domain gap between training and testing data and thus reduces the generalization error of a fPAD model. We introduce the experimental setting to evaluate the proposed framework and carry out extensive experiments to provide various insights about the proposed method for fPAD.