Autoencoders for Open-Set Presentation Attack Detection
- 6 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 8 (2) , 192-206
Abstract
Face anti-spoofing (FAS) has gained significant attention due to its crucial role in ensuring the security of facial recognition systems. Despite numerous proposed methods for addressing various types of presentation attacks, there remains a gap in the existing literature, as most methods only tackle seen attack types and lack generalizability in real-world scenarios. This paper presents a novel method for face antispoofing, specifically focused on open-set scenarios. The proposed approach consists of an autoencoder exclusively trained to reconstruct bona fide data. The key idea is that features extracted using this model would exhibit poor quality for attack data, resulting in significantly higher reconstruction errors. Consequently, these low-quality features would differ from the well-reconstructed features of bona fide samples. Our method’s key novelty lies in the rich feature learning procedure that focuses on the properties of bona fide samples through an autoencoder formulation. The extracted features are used to train one-class classifiers using only bona fide samples. Experimental results on standard benchmarks such as RECOD-MPAD, WMCA, HQ-WMCA, Replay-Attack, OULU-NPU and MSU-MFSD datasets demonstrate the excellent performance of our proposed approach, placing it among state-of-the-art methods for metrics like Bona Fide Presentation Classification Error Rate (BPCER), Attack Presentation Classification Error Rate (APCER) and Average Classification Error Rate (ACER).Keywords
Funding Information
- National Research Foundation (Hórus #2023/12865-8)
- Foundation for Scientific and Technological Development in Health (302458/2022-0)
- Foundation for Scientific and Technological Development in Health (Aletheia 442229/2024-0)
This publication has 44 references indexed in Scilit:
- Integrating Fine-Grained Classification and Motion Relation Analysis for Face Anti-SpoofingIEEE Access, 2025
- A Novel High-Performance Face Anti-Spoofing Detection MethodIEEE Access, 2024
- Self-Attention and MLP Auxiliary Convolution for Face Anti-SpoofingIEEE Access, 2023
- One-Class Face Anti-spoofing Based on Attention Auto-encoder2021
- One-Class Learning Method Based on Live Correlation Loss for Face Anti-SpoofingIEEE Access, 2020
- MORA: A Generative Approach to Extract Spatiotemporal Information Applied to Gesture Recognition2018
- A competition on generalized software-based face presentation attack detection in mobile scenarios2017
- An Anomaly Detection Approach to Face Spoofing Detection: A New Formulation and Evaluation ProtocolIEEE Access, 2017
- A comparative study of texture measures with classification based on featured distributionsPattern Recognition, 1996
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987