Logo image
Back
An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
Conference proceeding   Open access

An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization

Fei Kong, Jinhao Duan, Ruipeng Ma, Hengtao Shen, Xiaoshuang Shi, Xiaofeng Zhu and Kaidi Xu
12th International Conference on Learning Representations, ICLR 2024
2024
url
https://proceedings.iclr.cc/paper_files/paper/2024/hash/ff73af253974e6144c4eddf896d3095a-Abstract-Conference.htmlView
Published, Version of Record (VoR) Open Open Access (License Unspecified)

Abstract

Recently, diffusion models have achieved remarkable success in generating tasks, including image and audio generation. However, like other generative models, diffusion models are prone to privacy issues. In this paper, we propose an efficient query-based membership inference attack (MIA), namely Proximal Initialization Attack (PIA), which utilizes groundtruth trajectory obtained by ϵ initialized in t = 0 and predicted point to infer memberships. Experimental results indicate that the proposed method can achieve competitive performance with only two queries that achieve at least 6 × efficiency than the previous SOTA baseline on both discrete-time and continuous-time diffusion models. Moreover, previous works on the privacy of diffusion models have focused on vision tasks without considering audio tasks. Therefore, we also explore the robustness of diffusion models to MIA in the text-to-speech (TTS) task, which is an audio generation task. To the best of our knowledge, this work is the first to study the robustness of diffusion models to MIA in the TTS task. Experimental results indicate that models with mel-spectrogram (image-like) output are vulnerable to MIA, while models with audio output are relatively robust to MIA. Code is available at https://github.com/kong13661/PIA.

Metrics

1 Record Views

Related content

Has preprint

Details

Logo image