# Can Foundation Models Generalise the Presentation Attack Detection Capabilities on ID Cards?

arXiv: https://arxiv.org/abs/2506.05263 · HTML: https://mlsanity.com/paper/2506.05263/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [MIDV-500: A Dataset for Identity Documents Analysis and Recognition on Mobile Devices in Video Stream](https://mlsanity.com/paper/1807.05786/) (2018)
- [MIDV-2020: A Comprehensive Benchmark Dataset for Identity Document Analysis](https://mlsanity.com/paper/2107.00396/) (2021)
- [Few-Shot Object Detection: A Comprehensive Survey](https://mlsanity.com/paper/2112.11699/) (2021)
- [FRoundation: Are Foundation Models Ready for Face Recognition?](https://mlsanity.com/paper/2410.23831/) (2024)
- [MIDV-2019: Challenges of the modern mobile-based document OCR](https://mlsanity.com/paper/1910.04009/) (2019)
- [Synthetic ID Card Image Generation for Improving Presentation Attack Detection](https://mlsanity.com/paper/2211.00098/) (2022)
- [First Competition on Presentation Attack Detection on ID Card](https://mlsanity.com/paper/2409.00372/) (2024)
- [FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection](https://mlsanity.com/paper/2501.02892/) (2025)
- [Iris-SAM: Iris Segmentation Using a Foundation Model](https://mlsanity.com/paper/2402.06497/) (2024)
- [IDNet: A Novel Dataset for Identity Document Analysis and Fraud Detection](https://mlsanity.com/paper/2408.01690/) (2024)
- [Towards Iris Presentation Attack Detection with Foundation Models](https://mlsanity.com/paper/2501.06312/) (2025)
- [Few-Shot Learning: Expanding ID Cards Presentation Attack Detection to Unknown ID Countries](https://mlsanity.com/paper/2409.06842/) (2024)
- [SynID: Passport Synthetic Dataset for Presentation Attack Detection](https://mlsanity.com/paper/2505.07540/) (2025)
- [Synthetic dataset of ID and Travel Document](https://mlsanity.com/paper/2401.01858/) (2024)

## Built on by (most cited first, 2 of 2)

- [Identity Card Presentation Attack Detection: A Systematic Review](https://mlsanity.com/paper/2511.06056/) (2025)
- [From Vision to Text: A Compact Multimodal Approach for Robust, Cross-Domain Presentation Attack Detection on ID Cards](https://mlsanity.com/paper/2606.06966/) (2026)

## Abstract (arXiv)

Nowadays, one of the main challenges in presentation attack detection (PAD) on ID cards is obtaining generalisation capabilities for a diversity of countries that are issuing ID cards. Most PAD systems are trained on one, two, or three ID documents because of privacy protection concerns. As a result, they do not obtain competitive results for commercial purposes when tested in an unknown new ID card country. In this scenario, Foundation Models (FM) trained on huge datasets can help to improve generalisation capabilities. This work intends to improve and benchmark the capabilities of FM and how to use them to adapt the generalisation on PAD of ID Documents. Different test protocols were used, considering zero-shot and fine-tuning and two different ID card datasets. One private dataset based on Chilean IDs and one open-set based on three ID countries: Finland, Spain, and Slovakia. Our findings indicate that bona fide images are the key to generalisation.