Tomatoes, Potatoes, and Onions: Questioning the Need for Faces in Face Presentation Attack Detection

• URL: http://arxiv.org/abs/2608.21455v2
• Date: Thu, 27 Aug 2026 12:40:21 GMT
• Title: Tomatoes, Potatoes, and Onions: Questioning the Need for Faces in Face Presentation Attack Detection
• Abstract summary: We show that a detector trained on TPO achieves an average AUC of 92.70% across four standard cross-dataset face PAD benchmarks.<n>We also show that incorporating TPO into conventional face PAD training consistently improves cross-dataset performance.
• Score: 17.80271625273524
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Face presentation attack detection (PAD) is traditionally formulated as a face-specific problem, although many of the visual artifacts introduced by print, replay, and recapture processes are not inherently tied to facial appearance. In this work, we investigate whether transferable PAD representations can be learned without using faces during downstream PAD training. To this end, we introduce TPO, a controlled face-free presentation attack dataset consisting of bona fide, print, and replay recordings of, almost randomly chosen, tomatoes, potatoes, and onions acquired under protocols that closely mirror conventional face PAD datasets. Using a foundation-model-based PAD architecture, we demonstrate that a detector trained on TPO achieves an average AUC of 92.70% across four standard cross-dataset face PAD benchmarks, outperforming training on synthetic faces and remaining competitive with models trained on real face datasets. Conversely, models trained on face PAD datasets transfer consistently above chance to TPO, suggesting that the learned representations capture characteristics of the presentation process rather than object semantics. Furthermore, incorporating TPO into conventional face PAD training consistently improves cross-dataset performance under fixed optimization budgets, indicating that face-free data provides complementary information rather than simply additional training samples. Finally, representation and frequency analyses provide further evidence that transferable PAD representations cannot be explained by a single spectral artifact but instead encode richer presentation cues shared across object categories. Together, these results provide empirical evidence that transferable presentation attack representations can be learned independently of facial content, opening new opportunities for privacy-preserving and identity-independent PAD development.

Related papers

• Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark [32.89408229880636]
  Face presentation attack detection remains challenging under cross-dataset evaluation.<n>Do general-purpose vision foundation models encode PAD-relevant information accessible with minimal task-specific training?<n>We evaluate 24 frozen encoders, including self-supervised vision transformers, vision-language encoders, and supervised CNNs.
  arXiv  Detail & Related papers  (2026-07-29T14:52:25Z)
• Are Foundation Models All You Need for Zero-shot Face Presentation Attack Detection? [7.287930923353593]
  Face recognition systems are vulnerable to attack presentations (AP)<n>This paper focuses on zero-shot presentation attack detection (PAD) approaches.<n>We first assess the effectiveness and generalisability of foundation models in established and challenging experimental scenarios.
  arXiv  Detail & Related papers  (2025-07-22T09:38:21Z)
• Test-Time Augmentation for Pose-invariant Face Recognition [14.515296731166721]
  Pose-TTA is a novel approach that aligns faces at inference time without additional training.<n>To achieve this, we employ a portrait animator that transfers the source image identity into the pose of a driving image.<n>We propose a weighted feature aggregation strategy to address any distortions or biases arising from the synthetic data.
  arXiv  Detail & Related papers  (2025-05-14T10:11:35Z)
• Federated Face Forgery Detection Learning with Personalized Representation [63.90408023506508]
  Deep generator technology can produce high-quality fake videos that are indistinguishable, posing a serious social threat. Traditional forgery detection methods directly centralized training on data. The paper proposes a novel federated face forgery detection learning with personalized representation.
  arXiv  Detail & Related papers  (2024-06-17T02:20:30Z)
• Generalized Face Liveness Detection via De-fake Face Generator [52.23271636362843]
  Previous Face Anti-spoofing (FAS) methods face the challenge of generalizing to unseen domains.<n>We propose an Anomalous cue Guided FAS (AG-FAS) method, which can effectively leverage large-scale additional real faces.<n>Our method achieves state-of-the-art results under cross-domain evaluations with unseen scenarios and unknown presentation attacks.
  arXiv  Detail & Related papers  (2024-01-17T06:59:32Z)
• Towards Real-World Blind Face Restoration with Generative Diffusion Prior [69.84480964328465]
  Blind face restoration is an important task in computer vision and has gained significant attention due to its wide-range applications. We propose BFRffusion which is thoughtfully designed to effectively extract features from low-quality face images. We also build a privacy-preserving face dataset called PFHQ with balanced attributes like race, gender, and age.
  arXiv  Detail & Related papers  (2023-12-25T14:16:24Z)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• Fairness in Face Presentation Attack Detection [14.995906718043809]
  Face recognition algorithms have been proven to exhibit discriminatory behaviors against certain demographic and non-demographic groups. Despite the growing number of fairness studies in FR, the fairness of face presentation attack detection has been overlooked.
  arXiv  Detail & Related papers  (2022-09-19T14:12:09Z)
• One-Class Knowledge Distillation for Face Presentation Attack Detection [53.30584138746973]
  This paper introduces a teacher-student framework to improve the cross-domain performance of face PAD with one-class domain adaptation. Student networks are trained to mimic the teacher network and learn similar representations for genuine face samples of the target domain. In the test phase, the similarity score between the representations of the teacher and student networks is used to distinguish attacks from genuine ones.
  arXiv  Detail & Related papers  (2022-05-08T06:20:59Z)
• Myope Models -- Are face presentation attack detection models short-sighted? [3.4376560669160394]
  Presentation attacks are recurrent threats to biometric systems, where impostors attempt to bypass these systems. This work presents a comparative study of face presentation attack detection (PAD) models with and without crops. The results show that the performance is consistently better when the background is present in the images.
  arXiv  Detail & Related papers  (2021-11-22T11:28:44Z)
• Federated Test-Time Adaptive Face Presentation Attack Detection with Dual-Phase Privacy Preservation [100.69458267888962]
  Face presentation attack detection (fPAD) plays a critical role in the modern face recognition pipeline. Due to legal and privacy issues, training data (real face images and spoof images) are not allowed to be directly shared between different data sources. We propose a Federated Test-Time Adaptive Face Presentation Attack Detection with Dual-Phase Privacy Preservation framework.
  arXiv  Detail & Related papers  (2021-10-25T02:51:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.