Spoof Trace Discovery for Deep Learning Based Explainable Face Anti-Spoofing

TL;DR

This paper introduces X-FAS, a new explainable face anti-spoofing framework that discovers spoof traces to provide reliable explanations, enhancing trust and understanding in face recognition systems.

Contribution

The paper proposes SPTD, a novel method for discovering spoof traces, and establishes an X-FAS benchmark with expert-annotated spoof traces for evaluation.

Findings

SPTD effectively discovers spoof concepts and provides reliable explanations.

Experimental results show SPTD outperforms previous XAI methods in explanation quality.

The X-FAS benchmark facilitates standardized evaluation of explainable face anti-spoofing methods.

Abstract

With the rapid growth usage of face recognition in people's daily life, face anti-spoofing becomes increasingly important to avoid malicious attacks. Recent face anti-spoofing models can reach a high classification accuracy on multiple datasets but these models can only tell people "this face is fake" while lacking the explanation to answer "why it is fake". Such a system undermines trustworthiness and causes user confusion, as it denies their requests without providing any explanations. In this paper, we incorporate XAI into face anti-spoofing and propose a new problem termed X-FAS (eXplainable Face Anti-Spoofing) empowering face anti-spoofing models to provide an explanation. We propose SPTD (SPoof Trace Discovery), an X-FAS method which can discover spoof concepts and provide reliable explanations on the basis of discovered concepts. To evaluate the quality of X-FAS methods, we propose an X-FAS benchmark with annotated spoof traces by experts. We analyze SPTD explanations on face anti-spoofing dataset and compare SPTD quantitatively and qualitatively with previous XAI methods on proposed X-FAS benchmark. Experimental results demonstrate SPTD's ability to generate reliable explanations.