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

arXiv: https://arxiv.org/abs/2410.07988 · HTML: https://mlsanity.com/paper/2410.07988/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://mlsanity.com/paper/2111.15640/) (2021)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Face Morphing Attack Generation & Detection: A Comprehensive Survey](https://mlsanity.com/paper/2011.02045/) (2020)
- [MorDIFF: Recognition Vulnerability and Attack Detectability of Face Morphing Attacks Created by Diffusion Autoencoders](https://mlsanity.com/paper/2302.01843/) (2023)
- [Morphing Attack Potential](https://mlsanity.com/paper/2204.13374/) (2022)
- [Leveraging Diffusion For Strong and High Quality Face Morphing Attacks](https://mlsanity.com/paper/2301.04218/) (2023)
- [Approximating Optimal Morphing Attacks using Template Inversion](https://mlsanity.com/paper/2402.00695/) (2024)
- [Multi-Channel Cross Modal Detection of Synthetic Face Images](https://mlsanity.com/paper/2311.16773/) (2023)

## Built on by (most cited first, 9 of 9)

- [FLOWING: Implicit Neural Flows for Structure-Preserving Morphing](https://mlsanity.com/paper/2510.09537/) (2025)
- [Metric for Evaluating Performance of Reference-Free Demorphing Methods](https://mlsanity.com/paper/2501.12319/) (2025)
- [StableMorph: High-Quality Face Morph Generation with Stable Diffusion](https://mlsanity.com/paper/2511.08090/) (2025)
- [MorphGuard: Morph Specific Margin Loss for Enhancing Robustness to Face Morphing Attacks](https://mlsanity.com/paper/2505.10497/) (2025)
- [Arc2Morph: Identity-Preserving Facial Morphing with Arc2Face](https://mlsanity.com/paper/2602.16569/) (2026)
- [DifFoundMAD: Foundation Models meet Differential Morphing Attack Detection](https://mlsanity.com/paper/2604.17961/) (2026)
- [Enhancing Single-Image Facial Demorphing using Multimodal Large Language Models](https://mlsanity.com/paper/2605.25442/) (2026)
- [MorphUNet: Alpha-Controlled Biometric Transport for Diffusion-Based Face Morphing Attacks](https://mlsanity.com/paper/2607.25092/) (2026)
- [SCOUT: Semantic Concept Discovery for Open-Vocabulary Editing of face Recognition Templates](https://mlsanity.com/paper/2608.16251/) (2026)

## Abstract (arXiv)

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