mlsanityData to 7 Oct 2026

Detection and Continual Learning of Novel Face Presentation Attacks

arXiv 2108.12081 ↗First posted 27 Aug 2021cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Advances in deep learning, combined with availability of large datasets, have led to impressive improvements in face presentation attack detection research. However, state-of-the-art face antispoofing systems are still vulnerable to novel types of attacks that are never seen during training. Moreover, even if such attacks are correctly detected, these systems lack the ability to adapt to newly encountered attacks. The post-training ability of continually detecting new types of attacks and self-adaptation to identify these attack types, after the initial detection phase, is highly appealing. In this paper, we enable a deep neural network to detect anomalies in the observed input data points as potential new types of attacks by suppressing the confidence-level of the network outside the training samples' distribution. We then use experience replay to update the model to incorporate knowledge about new types of attacks without forgetting the past learned attack types. Experimental results are provided to demonstrate the effectiveness of the proposed method on two benchmark datasets as well as a newly introduced dataset which exhibits a large variety of attack types.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 29 of its 56 references that are in the map. First posted on arXiv 27 Aug 2021.

Builds on

29 of 56 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  6. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  7. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  8. 2017Continual Learning with Deep Generative Replaycited by 1,152
  9. 2015Prioritized Experience Replaycited by 1,070
  10. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 511
  11. 2020Searching Central Difference Convolutional Networks for Face Anti-Spoofingcited by 173
  12. 2018Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervisioncited by 167
17 more
  1. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  2. 2019Deep Tree Learning for Zero-shot Face Anti-Spoofingcited by 73
  3. 2020Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofingcited by 70
  4. 2020Face Anti-Spoofing with Human Material Perceptioncited by 62
  5. 2019CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofingcited by 61
  6. 2018Face De-Spoofing: Anti-Spoofing via Noise Modelingcited by 60
  7. 2017Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANscited by 55
  8. 2019Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replaycited by 51
  9. 2020Unsupervised Model Adaptation for Continual Semantic Segmentationcited by 42
  10. 2020Learning One Class Representations for Face Presentation Attack Detection using Multi-channel Convolutional Neural Networkscited by 36
  11. 2020Deep Models and Shortwave Infrared Information to Detect Face Presentation Attackscited by 29
  12. 2019Generative Continual Concept Learningcited by 26
  13. 2017Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfercited by 19
  14. 2019Deep Anomaly Detection for Generalized Face Anti-Spoofingcited by 17
  15. 2019Generating Accurate Pseudo-labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activationscited by 13
  16. 2017Joint Dictionaries for Zero-Shot Learningcited by 9
  17. 2020Multispectral Biometrics System Framework: Application to Presentation Attack Detectioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 11; 2024: 3; 2025: 10; 2026: 2.

33 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2022UC-OWOD: Unknown-Classified Open World Object Detectioncited by 40
  3. 2022Multi-domain Learning for Updating Face Anti-spoofing Modelscited by 39
  4. 2022Benchmarking Joint Face Spoofing and Forgery Detection with Visual and Physiological Cuescited by 24
  5. 2025Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Modelscited by 23
  6. 2023SynthASpoof: Developing Face Presentation Attack Detection Based on Privacy-friendly Synthetic Datacited by 17
  7. 2022Fairness in Face Presentation Attack Detectioncited by 13
  8. 2023Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Lesscited by 12
  9. 2023Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillationcited by 11
  10. 2021Consistency Regularization for Deep Face Anti-Spoofingcited by 10
  11. 2024Dynamic Transformer Architecture for Continual Learning of Multimodal Taskscited by 8
  12. 2024DiffFAS: Face Anti-Spoofing via Generative Diffusion Modelscited by 7
21 more
  1. 2025FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Modelscited by 6
  2. 2023Improved Region Proposal Network for Enhanced Few-Shot Object Detectioncited by 5
  3. 2023Adversarial Robust Memory-Based Continual Learnercited by 5
  4. 2025SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretrainingcited by 5
  5. 2025Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuningcited by 5
  6. 2023Domain-Generalized Face Anti-Spoofing with Unknown Attackscited by 4
  7. 2025DADM: Dual Alignment of Domain and Modality for Face Anti-spoofingcited by 4
  8. 2025FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detectioncited by 3
  9. 2021Explaining Face Presentation Attack Detection Using Natural Languagecited by 2
  10. 2023Encoding Binary Concepts in the Latent Space of Generative Models for Enhancing Data Representationcited by 2
  11. 2023Hyperbolic Face Anti-Spoofingcited by 1
  12. 2023IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Imagescited by 1
  13. 2022Face Presentation Attack Detectioncited by 0
  14. 2023Robust Internal Representations for Domain Generalizationcited by 0
  15. 2024Unsupervised Domain Adaptation Using Compact Internal Representationscited by 0
  16. 2025Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichmentcited by 0
  17. 2025Multi-Modal Face Anti-Spoofing via Cross-Modal Feature Transitionscited by 0
  18. 2025Robust Multi-Modal Face Anti-Spoofing with Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-Labels, and Model Degradationcited by 0
  19. 2025Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detectioncited by 0
  20. 2026CLeAN: Continual Learning Adaptive Normalization in Dynamic Environmentscited by 0
  21. 2026Forensic-Aware Continual Adaptation for Image Forgery Localizationcited by 0