Conference proceeding
Are Diffusion Models Vulnerable to Membership Inference Attacks?
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 202, v 202, pp 8717-8730
01 Jan 2023
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
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 diffusion models to Membership Inference Attacks (MIAs), a common privacy concern. Our results indicate that existing MIAs designed for GANs or VAE are largely ineffective on diffusion models, either due to inapplicable scenarios (e.g., requiring the discriminator of GANs) or inappropriate assumptions (e.g., closer distances between synthetic samples and member samples). To address this gap, we propose Step-wise Error Comparing Membership Inference (SecMI), a query-based MIA that infers memberships by assessing the matching of forward process posterior estimation at each timestep. SecMI follows the common overfitting assumption in MIA where member samples normally have smaller estimation errors, compared with hold-out samples. We consider both the standard diffusion models, e.g., DDPM, and the text-to-image diffusion models, e.g., Latent Diffusion Models and Stable Diffusion. Experimental results demonstrate that our methods precisely infer the membership with high confidence on both of the two scenarios across multiple different datasets. Code is available at https: //github.com/jinhaoduan/SecMI.
Metrics
1 Record Views
Details
- Title
- Are Diffusion Models Vulnerable to Membership Inference Attacks?
- Creators
- Jinhao Duan - Drexel UniversityFei Kong - Univ Elect Sci & Technol China, Hefei, Anhui, Peoples R ChinaShiqi Wang - The Art InstitutesXiaoshuang Shi - Univ Elect Sci & Technol China, Hefei, Anhui, Peoples R ChinaKaidi Xu - Drexel University
- Contributors
- A Krause (Editor)E Brunskill (Editor)K Cho (Editor)B Engelhardt (Editor)S Sabato (Editor)J Scarlett (Editor)
- Publication Details
- INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 202, v 202, pp 8717-8730
- Series
- Proceedings of Machine Learning Research
- Publisher
- JMLR-JOURNAL MACHINE LEARNING RESEARCH
- Number of pages
- 14
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:001371932500032
- Scopus ID
- 2-s2.0-85174416063
- Other Identifier
- 991022207060904721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
Source: SDGs in the Output
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Theory & Methods