Yan Pang (University of Virginia), Tianhao Wang (University of Virginia)

With the rapid advancement of diffusion-based image-generative models, the quality of generated images has become increasingly photorealistic. Moreover, with the release of high-quality pre-trained image-generative models, a growing number of users are downloading these pre-trained models to fine-tune them with downstream datasets for various image-generation tasks. However, employing such powerful pre-trained models in downstream tasks presents significant privacy leakage risks. In this paper, we propose the first scores-based membership inference attack framework tailored for recent diffusion models, and in the more stringent black-box access setting. Considering four distinct attack scenarios and three types of attacks, this framework is capable of targeting any popular conditional generator model, achieving high precision, evidenced by an impressive AUC of 0.95.

View More Papers

Vulnerability, Where Art Thou? An Investigation of Vulnerability Management...

Daniel Klischies (Ruhr University Bochum), Philipp Mackensen (Ruhr University Bochum), Veelasha Moonsamy (Ruhr University Bochum)

Read More

A Method to Facilitate Membership Inference Attacks in Deep...

Zitao Chen (University of British Columbia), Karthik Pattabiraman (University of British Columbia)

Read More

Revealing the Black Box of Device Search Engine: Scanning...

Mengying Wu (Fudan University), Geng Hong (Fudan University), Jinsong Chen (Fudan University), Qi Liu (Fudan University), Shujun Tang (QI-ANXIN Technology Research Institute; Tsinghua University), Youhao Li (QI-ANXIN Technology Research Institute), Baojun Liu (Tsinghua University), Haixin Duan (Tsinghua University; Quancheng Laboratory), Min Yang (Fudan University)

Read More