MorCode: Face Morphing Attack Generation using Generative Codebooks

TL;DR

This paper introduces MorCode, a novel encoder-decoder based face morphing method leveraging codebook learning, which produces high-quality morphs and demonstrates high attack potential against face recognition systems.

Contribution

MorCode is a new face morphing technique using codebook-conditioned generative architecture, outperforming existing methods in attack effectiveness on digital and print-scan data.

Findings

MorCode achieves the highest attack success rate among tested methods.

It performs well on both digital and print-scan face data.

Extensive experiments validate its effectiveness against multiple face recognition systems.

Abstract

Face recognition systems (FRS) can be compromised by face morphing attacks, which blend textural and geometric information from multiple facial images. The rapid evolution of generative AI, especially Generative Adversarial Networks (GAN) or Diffusion models, where encoded images are interpolated to generate high-quality face morphing images. In this work, we present a novel method for the automatic face morphing generation method \textit{MorCode}, which leverages a contemporary encoder-decoder architecture conditioned on codebook learning to generate high-quality morphing images. Extensive experiments were performed on the newly constructed morphing dataset using five state-of-the-art morphing generation techniques using both digital and print-scan data. The attack potential of the proposed morphing generation technique, \textit{MorCode}, was benchmarked using three different face recognition systems. The obtained results indicate the highest attack potential of the proposed \textit{MorCode} when compared with five state-of-the-art morphing generation methods on both digital and print scan data.