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

PBP: Post-training Backdoor Purification for Malware Classifiers

Dung Thuy Nguyen (Vanderbilt University), Ngoc N. Tran (Vanderbilt University), Taylor T. Johnson (Vanderbilt University), Kevin Leach (Vanderbilt University)

Read More

Mnemocrypt

André Pacteau, Antonino Vitale, Davide Balzarotti, Simone Aonzo (EURECOM)

Read More

”Who is Trying to Access My Account?” Exploring User...

Tongxin Wei (Nankai University), Ding Wang (Nankai University), Yutong Li (Nankai University), Yuehuan Wang (Nankai University)

Read More

type++: Prohibiting Type Confusion with Inline Type Information

Nicolas Badoux (EPFL), Flavio Toffalini (Ruhr-Universität Bochum, EPFL), Yuseok Jeon (UNIST), Mathias Payer (EPFL)

Read More