Membership Inference Attacks for Face Images Against Fine-Tuned Latent Diffusion Models

Lauritz Holme, Anton Mosquera Storgaard, Siavash Arjomand Bigdeli

2025

Abstract

The rise of generative image models leads to privacy concerns when it comes to the huge datasets used to train such models. This paper investigates the possibility of inferring if a set of face images was used for fine-tuning a Latent Diffusion Model (LDM). A Membership Inference Attack (MIA) method is presented for this task. Using generated auxiliary data for the training of the attack model leads to significantly better performance, and so does the use of watermarks. The guidance scale used for inference was found to have a significant influence. If a LDM is fine-tuned for long enough, the text prompt used for inference has no significant influence. The proposed MIA is found to be viable in a realistic black-box setup against LDMs fine-tuned on face-images.

Paper Citation

in Harvard Style

Holme L., Storgaard A. and Bigdeli S. (2025). Membership Inference Attacks for Face Images Against Fine-Tuned Latent Diffusion Models. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 439-446. DOI: 10.5220/0013182600003912

in Bibtex Style

@conference{visapp25,
author={Lauritz Holme and Anton Storgaard and Siavash Bigdeli},
title={Membership Inference Attacks for Face Images Against Fine-Tuned Latent Diffusion Models},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={439-446},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013182600003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Membership Inference Attacks for Face Images Against Fine-Tuned Latent Diffusion Models
SN - 978-989-758-728-3
AU - Holme L.
AU - Storgaard A.
AU - Bigdeli S.
PY - 2025
SP - 439
EP - 446
DO - 10.5220/0013182600003912
PB - SciTePress