Cascade Forgery Mining Network for Fingerprint Presentation Attack Detection

2026-07-27

AI Summary

This work addresses the significant variation in the difficulty of extracting spoofing artifacts across different fingerprint regions by proposing an adaptive detection framework based on Artifact Extraction Difficulty. The method quantifies the certainty of local Gabor features to assess regional spoofing complexity and constructs a cascaded forgery mining network with adaptive depth. Additionally, it incorporates an Orientation-Guided Adversarial Training (OGAT) module to preserve critical artifact evidence while suppressing identity-related interference. Evaluated on the LivDet benchmark, the proposed approach substantially outperforms existing state-of-the-art methods, demonstrating particularly notable improvements in detecting presentation attacks in high-difficulty regions.

Abstract

Fingerprint Presentation Attack Detection (PAD) is a critical component of fingerprint identification systems, serving as a protective measure against unauthorized access. In this paper, we observe that different regions of a fingerprint image can exhibit varying Artifact Extraction Difficulty (AED), with high-AED regions requiring more sophisticated extraction mechanisms to capture more subtle discriminative evidence. To address this issue, we propose to quantify AED using local Gabor feature certainty and partition fingerprint images into multiple regions based on their respective AED values. We then propose an AED guided Cascade Forgery Mining Network (CFM-Net) that employs an adaptive-depth feature extraction architecture to detect more precise and comprehensive artifact evidence across regions with heterogeneous AED values. Furthermore, we introduce an Orientation Guided Adversarial Training (OGAT) module to filter out identity information from PAD features while preserving the integrity of original artifact evidence. Experimental evaluations on LivDet datasets demonstrate the superior performance of our approach compared to state-of-the-art methods and achieve significant improvement in the classification ability of high AED fingerprints.

Problem

• Fingerprint Presentation Attack Detection
• Artifact Extraction Difficulty
• Gabor features
• Adversarial Training
• LivDet

Innovation

• Cascade Forgery Mining Network
• Artifact Extraction Difficulty
• Orientation Guided Adversarial Training
• Fingerprint Presentation Attack Detection
• Adaptive-depth Feature Extraction