# Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark

arXiv: https://arxiv.org/abs/2607.26993 · HTML: https://mlsanity.com/paper/2607.26993/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 67 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Builds on (most cited first, 30 of 46)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Masked Siamese Networks for Label-Efficient Learning](https://mlsanity.com/paper/2204.07141/) (2022)
- [Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision](https://mlsanity.com/paper/1803.11097/) (2018)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [Single-Side Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2004.14043/) (2020)
- [CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations](https://mlsanity.com/paper/2007.12342/) (2020)
- [NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing](https://mlsanity.com/paper/2011.02062/) (2020)
- [Regularized Fine-grained Meta Face Anti-spoofing](https://mlsanity.com/paper/1911.10771/) (2019)
- [Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection](https://mlsanity.com/paper/1907.04047/) (2019)
- [PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition](https://mlsanity.com/paper/2203.14325/) (2022)
- [Generalizable Representation Learning for Mixture Domain Face Anti-Spoofing](https://mlsanity.com/paper/2105.02453/) (2021)
- [Revisiting Pixel-Wise Supervision for Face Anti-Spoofing](https://mlsanity.com/paper/2011.12032/) (2020)
- [FLIP: Cross-domain Face Anti-spoofing with Language Guidance](https://mlsanity.com/paper/2309.16649/) (2023)

## Built on by (most cited first, 1 of 1)

- [Foundation and Multimodal Large Language Models for Face Presentation and Morph Attack Detection](https://mlsanity.com/paper/2608.29802/) (2026)

## Abstract (arXiv)

Face presentation attack detection (PAD) remains challenging under cross-dataset evaluation, where domain shift degrades models trained on a single dataset. The scarcity of large-scale labeled data motivates adapting pretrained vision models rather than training task-specific architectures from scratch, raising a fundamental question: do general-purpose vision foundation models encode PAD-relevant information accessible with minimal task-specific training? To investigate, we systematically evaluate 24 frozen encoders, including self-supervised vision transformers, vision-language encoders, and supervised CNNs, using a unified linear-probing protocol on the MCIO benchmark (MSU-MFSD, CASIA-FASD, Replay-Attack, OULU-NPU). The backbone remains fixed, and only a lightweight linear head is trained to isolate the PAD information already present in the pretrained representation. Results show that frozen foundation-model representations can support strong intra-dataset PAD performance with only a linear classifier, but this performance does not reliably transfer across datasets. Model scale is beneficial within several families, although the effect is not monotonic and is strongly mediated by architecture and pretraining. InternViT-6B achieves the lowest mean intra-dataset error, whereas CLIP ViT-B/32 offers the most favorable cross-dataset transfer-compute trade-off among the evaluated probes. These findings suggest that while pretrained representations contain PAD-relevant information, explicit adaptation remains necessary to address domain shift.