Files and links (1)
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute, Open
Preprint
An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
arXiv.org
26 May 2023
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
$\epsilon$ 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 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
\url{https://github.com/kong13661/PIA}}.
Metrics
19 Record Views
Details
- Title
- An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
- Creators
- Fei KongJinhao DuanRuiPeng MaHengtao ShenXiaofeng ZhuXiaoshuang ShiKaidi Xu
- Publication Details
- arXiv.org
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Computer Science (Computing)
- Other Identifier
- 991021871486104721