Towards More Realistic Membership Inference Attacks on Large Diffusion Models

by   Jan Dubiński, et al.
Politechnika Warszawska

Generative diffusion models, including Stable Diffusion and Midjourney, can generate visually appealing, diverse, and high-resolution images for various applications. These models are trained on billions of internet-sourced images, raising significant concerns about the potential unauthorized use of copyright-protected images. In this paper, we examine whether it is possible to determine if a specific image was used in the training set, a problem known in the cybersecurity community and referred to as a membership inference attack. Our focus is on Stable Diffusion, and we address the challenge of designing a fair evaluation framework to answer this membership question. We propose a methodology to establish a fair evaluation setup and apply it to Stable Diffusion, enabling potential extensions to other generative models. Utilizing this evaluation setup, we execute membership attacks (both known and newly introduced). Our research reveals that previously proposed evaluation setups do not provide a full understanding of the effectiveness of membership inference attacks. We conclude that the membership inference attack remains a significant challenge for large diffusion models (often deployed as black-box systems), indicating that related privacy and copyright issues will persist in the foreseeable future.


page 12

page 20


Are Diffusion Models Vulnerable to Membership Inference Attacks?

Diffusion-based generative models have shown great potential for image s...

Membership Inference of Diffusion Models

Recent years have witnessed the tremendous success of diffusion models i...

HoloDiffusion: Training a 3D Diffusion Model using 2D Images

Diffusion models have emerged as the best approach for generative modeli...

Membership Inference Attacks against Diffusion Models

Diffusion models have attracted attention in recent years as innovative ...

Scalable Membership Inference Attacks via Quantile Regression

Membership inference attacks are designed to determine, using black box ...

A Probabilistic Fluctuation based Membership Inference Attack for Diffusion Models

Membership Inference Attack (MIA) identifies whether a record exists in ...

DAMIA: Leveraging Domain Adaptation as a Defense against Membership Inference Attacks

Deep Learning (DL) techniques allow ones to train models from a dataset ...

Please sign up or login with your details

Forgot password? Click here to reset