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

TL;DR

This paper introduces LADIMO, a novel face morphing method using latent diffusion to invert biometric templates, significantly enhancing the diversity and effectiveness of face morphing attacks for security testing.

Contribution

LADIMO is the first to perform face morphing at the representation level using latent diffusion, enabling unlimited attack variations and improving attack success rates over existing GAN-based methods.

Findings

LADIMO outperforms MIPGAN-II in morph attack potential.

The model enables unlimited morphing attacks from a single image pair.

Re-sampling enhances attack success rate diversity.

Abstract

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. Code and pre-trained models available here: https://github.com/dasec/LADIMO