A Unified Framework for Iris Anti-Spoofing: Introducing Iris Anti-Spoofing Cross-Domain-Testing Protocol and Masked-MoE Method

2024-08-19

AI Summary

Iris anti-spoofing (IAS) lacks systematic cross-domain robustness evaluation, and model generalization is hindered by device heterogeneity and demographic diversity. Method: This paper introduces IAS-CDT—the first systematic cross-domain evaluation framework for IAS—encompassing 10 datasets, 7 databases, 6 acquisition device types, and 3 sub-protocols. It further proposes Masked-MoE, a novel mixture-of-experts architecture that mitigates overfitting via token masking and consistency constraints on expert outputs. Results: Under a unified evaluation protocol, Masked-MoE achieves an average 4.2% AUC improvement over standard MoE. This work establishes the first open-source, reproducible cross-domain benchmark for iris anti-spoofing and introduces a co-design paradigm integrating model architecture innovation with evaluation methodology optimization.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Adversarial Attacks & Robustness
• Application Domains: Mobility, Driving & Flight

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Iris recognition is widely used in high-security scenarios due to its stability and distinctiveness. However, iris images captured by different devices exhibit certain and device-related consistent differences, which has a greater impact on the classification algorithm for anti-spoofing. The iris of various races would also affect the classification, causing the risk of identity theft. So it is necessary to improve the cross-domain capabilities of the iris anti-spoofing (IAS) methods to enable it more robust in facing different races and devices. However, there is no existing protocol that is comprehensively available. To address this gap, we propose an Iris Anti-Spoofing Cross-Domain-Testing (IAS-CDT) Protocol, which involves 10 datasets, belonging to 7 databases, published by 4 institutions, and collected with 6 different devices. It contains three sub-protocols hierarchically, aimed at evaluating average performance, cross-racial generalization, and cross-device generalization of IAS models. Moreover, to address the cross-device generalization challenge brought by the IAS-CDT Protocol, we employ multiple model parameter sets to learn from the multiple sub-datasets. Specifically, we utilize the Mixture of Experts (MoE) to fit complex data distributions using multiple sub-neural networks. To further enhance the generalization capabilities, we propose a novel method Masked-MoE (MMoE), which randomly masks a portion of tokens for some experts and requires their outputs to be similar to the unmasked experts, which can effectively mitigate the overfitting issue of MoE. For the evaluation, we selected ResNet50, VIT-B/16, CLIP, and FLIP as representative models and benchmarked them under the proposed IAS-CDT Protocol.

Problem

• Enhancing cross-domain iris anti-spoofing for diverse races and devices
• Introducing a comprehensive testing protocol (IAS-CDT) for iris anti-spoofing evaluation
• Proposing Masked-MoE method to improve generalization and reduce overfitting

Innovation

• Introduces Iris Anti-Spoofing Cross-Domain-Testing Protocol
• Proposes Masked-MoE method for cross-device generalization
• Utilizes Mixture of Experts to fit complex data