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

2025/06/05 by Juan Tapia, Christoph Busch, Tapia, Juan E. +1 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Benchmark (surveying) #Biometric Identification and Security #Bridge (graph theory) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Foundation (evidence) #Key (lock) #Presentation (obstetrics) #Smart card #Spam and Phishing Detection

paper · pdf · doi:10.48550/arxiv.2506.05263

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/06/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

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.

Citations

• SynID: Passport Synthetic Dataset for Presentation Attack Detection
• Towards Iris Presentation Attack Detection with Foundation Models
• FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection
• FRoundation: Are Foundation Models Ready for Face Recognition?
• Few-Shot Learning: Expanding ID Cards Presentation Attack Detection to Unknown ID Countries
• First Competition on Presentation Attack Detection on ID Card
• IDNet: A Novel Dataset for Identity Document Analysis and Fraud Detection
• YOLOv8: A Novel Object Detection Algorithm with Enhanced Performance and Robustness
• Iris-SAM: Iris Segmentation Using a Foundation Model
• Synthetic dataset of ID and Travel Document
• DINOv2: Learning Robust Visual Features without Supervision
• Synthetic ID Card Image Generation for Improving Presentation Attack Detection
• Few-Shot Object Detection: A Comprehensive Survey
• Swin Transformer V2: Scaling Up Capacity and Resolution
• Learning Transferable Visual Models From Natural Language Supervision
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Searching for MobileNetV3
• Image-to-Image Translation with Conditional Adversarial Networks
• Densely Connected Convolutional Networks
• Deep Residual Learning for Image Recognition

Cited by

• Identity Card Presentation Attack Detection: A Systematic Review

Related

• First Competition on Presentation Attack Detection on ID Card
• Few-Shot Learning: Expanding ID Cards Presentation Attack Detection to Unknown ID Countries
• ID-Card Synthetic Generation: Toward a Simulated Bona fide Dataset
• Second Competition on Presentation Attack Detection on ID Card
• Improving Presentation Attack Detection for ID Cards on Remote Verification Systems