Explainable Face Presentation Attack Detection via Ensemble-CAM

TL;DR

This paper introduces Ensemble-CAM, a novel visual explanation method for deep learning-based face presentation attack detection systems, aiming to improve transparency and trustworthiness by highlighting key decision regions.

Contribution

The paper proposes Ensemble-CAM, an innovative technique to generate visual explanations for face PAD models, enhancing interpretability and understanding of their decision-making process.

Findings

Ensemble-CAM effectively highlights key regions influencing PAD decisions.

The method improves transparency of deep learning face PAD systems.

Enhanced interpretability fosters greater trust in biometric security systems.

Abstract

Presentation attacks represent a critical security threat where adversaries use fake biometric data, such as face, fingerprint, or iris images, to gain unauthorized access to protected systems. Various presentation attack detection (PAD) systems have been designed leveraging deep learning (DL) models to mitigate this type of threat. Despite their effectiveness, most of the DL models function as black boxes - their decisions are opaque to their users. The purpose of explainability techniques is to provide detailed information about the reason behind the behavior or decision of DL models. In particular, visual explanation is necessary to better understand the decisions or predictions of DL-based PAD systems and determine the key regions due to which a biometric image is considered real or fake by the system. In this work, a novel technique, Ensemble-CAM, is proposed for providing visual explanations for the decisions made by deep learning-based face PAD systems. Our goal is to improve DL-based face PAD systems by providing a better understanding of their behavior. Our provided visual explanations will enhance the transparency and trustworthiness of DL-based face PAD systems.