LADIMO: Face Morph Generation through Biometric Template Inversion with Latent Diffusion

Face morphing attacks pose a severe security threat to face recognition systems, enabling the morphed face image to be verified against multiple identities. To detect such manipulated images, the development of new face morphing methods becomes essential to increase the diversity of training datasets used for face morph detection. In this study, we present a representation-level face morphing approach, namely LADIMO, that performs morphing on two face recognition embeddings. Specifically, we train a Latent Diffusion Model to invert a biometric template - thus reconstructing the face image from an FRS latent representation. Our subsequent vulnerability analysis demonstrates the high morph attack potential in comparison to MIPGAN-II, an established GAN-based face morphing approach. Finally, we exploit the stochastic LADMIO model design in combination with our identity conditioning mechanism to create unlimited morphing attacks from a single face morph image pair. We show that each face morph variant has an individual attack success rate, enabling us to maximize the morph attack potential by applying a simple re-sampling strategy. We will publish our code and pre-trained models upon the acceptance of this paper.

1. Introduction

Nowadays, face recognition systems (FRS) find application in critical areas such as border control [3] and forensics [6] [7] due to their high accuracy, uniqueness, and non-intrusiveness. However, despite these advantages, one of the main challenges remains the distinction between intra-identity and inter-identity variability necessary to discern mated from non-mated comparison trials. In this context, the security of FRS depends on the decision threshold at which a presented probe image is verified successfully against the stored reference.