paper-with-me

Papers

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 (Denoiser Ideal Membership Error), a theoretically grounded and query-efficient framework for membership inference on diffusion models. Our starting point is an exact characterization of the optimal diffusion denoiser for a finite training set, which reveals that membership leakage is governed by the denoiser's implicit reconstruction error. This error decomposes into two complementary signals: a bias term, capturing reconstruction accuracy, and a previously unexplored local crowding term, capturing the geometry of nearby training examples. Both admit efficient estimators using only model queries, yielding a practical attack with as few as two queries. Across CIFAR-10/100, STL10-U, CelebA, and ImageNet, DIME consistently outperforms prior attacks at comparable or substantially lower query cost, improving TPR at 1% FPR by up to $3\times$; remarkably, its two-query variant can outperform existing 30-query baselines. Finally, we suggest, discuss, and evaluate specific defenses to counteract such powerful membership tests.

📄 PDF Abstract BibTeX arXiv:2608.22824

Code (0)

등록된 구현이 없습니다.

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…

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

Score-based Membership Inference on Diffusion Models

2025-09-29 · Mingxing Rao, Bowen Qu, Daniel Moyer arxiv

Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of the training set. While existing methods typically rely on measuring reconstruc…

Membership Inference over Diffusion-models-based Synthetic Tabular Data

2025-10-16 · Peini Cheng, Amir Bahmani arxiv

This study investigates the privacy risks associated with diffusion-based synthetic tabular data generation methods, focusing on their susceptibility to Membership Inference Attacks (MIAs). We examine two recent models, …

Synthetic Data GenerationTabular Data Generation

Cascading and Proxy Membership Inference Attacks

2025-07-29 · Yuntao Du, Jiacheng Li, Yuetian Chen, Kaiyuan Zhang 외 arxiv

A Membership Inference Attack (MIA) assesses how much a trained machine learning model reveals about its training data by determining whether specific query instances were included in the dataset. We classify existing MI…