paper-with-me

Papers

Membership Inference of Diffusion Models

2023-01-24 · Hailong Hu, Jun Pang

Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to severe privacy concerns. In this paper, we systematically present the first study about membership inference attacks against diffusion models, which aims to infer whether a sample was used to train the model. Two attack methods are proposed, namely loss-based and likelihood-based attacks. Our attack methods are evaluated on several state-of-the-art diffusion models, over different datasets in relation to privacy-sensitive data. Extensive experimental evaluations show that our attacks can achieve remarkable performance. Furthermore, we exhaustively investigate various factors which can affect attack performance. Finally, we also evaluate the performance of our attack methods on diffusion models trained with differential privacy.

📄 PDF Abstract BibTeX arXiv:2301.09956

Code (1)

HailongHuPri/MIDM 공식 구현 jax

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models

2025-10-18 · Guo Li, Weihong Chen, Yongfu Fan arxiv

Diffusion models have demonstrated powerful performance in generating high-quality images. A typical example is text-to-image generator like Stable Diffusion. However, their widespread use also poses potential privacy ri…

Towards More Realistic Membership Inference Attacks on Large Diffusion Models

2023-06-22 · Jan Dubiński, Antoni Kowalczuk, Stanisław Pawlak, Przemysław Rokita 외

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-sour…

Inference AttackMembership Inference Attack

Are Diffusion Models Vulnerable to Membership Inference Attacks?

2023-02-02 · Jinhao Duan, Fei Kong, Shiqi Wang, Xiaoshuang Shi 외

Diffusion-based generative models have shown great potential for image synthesis, but there is a lack of research on the security and privacy risks they may pose. In this paper, we investigate the vulnerability of diffus…

Image Generation

DIME: Query-Efficient Framework for Membership Inference on Diffusion Models

2026-08-24 · Tue Do, Daniel Alabi arxiv

Membership inference attacks expose whether individual records were used to train a model, yet existing attacks on diffusion models are largely heuristic and can require substantial query budgets. We introduce DIME (Deno…

FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models

2026-05-12 · Abtin Mahyar, Masoumeh Shafieinejad, Yuhan Liu, Xi He arxiv

Diffusion models are the leading approach for tabular data synthesis and are increasingly used to share sensitive records. Whether they actually protect privacy has become a pressing question. Membership inference attack…