Generalizability of CNN Architectures for Face Morph Presentation Attack

TL;DR

This study evaluates the generalization ability of five CNN architectures in detecting face morphing attacks across diverse datasets, highlighting InceptionResNet-v2's superior performance in unseen data scenarios.

Contribution

It provides a comprehensive comparison of CNN architectures' robustness against morphing attacks across multiple datasets, emphasizing the importance of model selection for security applications.

Findings

InceptionResNet-v2 outperforms other CNNs in generalization.

Performance varies significantly across datasets.

Model robustness is crucial for border control security.

Abstract

Automatic border control systems are wide spread in modern airports worldwide. Morphing attacks on face biometrics is a serious threat that undermines the security and reliability of face recognition systems deployed in airports and border controls. Therefore, developing a robust Machine Learning (ML) system is necessary to prevent criminals crossing borders with fake identifications especially since it has been shown that security officers cannot detect morphs better than machines. In this study, we investigate the generalization power of Convolutional Neural Network (CNN) architectures against morphing attacks. The investigation utilizes 5 distinct CNNs namely ShuffleNet, DenseNet201, VGG16, EffecientNet-B0 and InceptionResNet-v2. Each CNN architecture represents a well-known family of CNN models in terms of number of parameters, architectural design and performance across various computer vision applications. To ensure robust evaluation, we employ 4 different datasets (Utrecht, London, Defacto and KurdFace) that contain a diverse range of digital face images which cover variations in ethnicity, gender, age, lighting condition and camera setting. One of the fundamental concepts of ML system design is the ability to generalize effectively to previously unseen data, hence not only we evaluate the performance of CNN models within individual datasets but also explore their performance across combined datasets and investigating each dataset in testing phase only. Experimental results on more than 8 thousand images (genuine and morph) from the 4 datasets show that InceptionResNet-v2 generalizes better to unseen data and outperforms the other 4 CNN models.