Robust Ensemble Morph Detection with Domain Generalization

TL;DR

This paper presents a robust ensemble approach combining CNNs and Transformers, trained with adversarial techniques, to improve generalization and robustness in face morph detection across various attacks and datasets.

Contribution

It introduces a novel ensemble model with adversarial training that enhances generalization and robustness in morph detection, outperforming existing methods.

Findings

The ensemble model generalizes well to multiple morphing attacks and datasets.

It achieves superior robustness against various adversarial attacks.

The approach outperforms state-of-the-art methods in accuracy and robustness.

Abstract

Although a substantial amount of studies is dedicated to morph detection, most of them fail to generalize for morph faces outside of their training paradigm. Moreover, recent morph detection methods are highly vulnerable to adversarial attacks. In this paper, we intend to learn a morph detection model with high generalization to a wide range of morphing attacks and high robustness against different adversarial attacks. To this aim, we develop an ensemble of convolutional neural networks (CNNs) and Transformer models to benefit from their capabilities simultaneously. To improve the robust accuracy of the ensemble model, we employ multi-perturbation adversarial training and generate adversarial examples with high transferability for several single models. Our exhaustive evaluations demonstrate that the proposed robust ensemble model generalizes to several morphing attacks and face datasets. In addition, we validate that our robust ensemble model gain better robustness against several adversarial attacks while outperforming the state-of-the-art studies.