CISPA
Browse

Quantifying Privacy Risks of Prompts in Visual Prompt Learning

Download (957.85 kB)
conference contribution
posted on 2024-02-09, 09:21 authored by Yixin Wu, Rui WenRui Wen, Michael BackesMichael Backes, Pascal Berrang, Mathias Humbert, Yun Shen, Yang ZhangYang Zhang
Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only learns an input perturbation, namely prompt, to be added to the downstream task data for predictions. Given the fast development of prompt learning, a well-generalized prompt inevitably becomes a valuable asset as significant effort and proprietary data are used to create it. This naturally raises the question of whether a prompt may leak the proprietary information of its training data. In this paper, we perform the first comprehensive privacy assessment of prompts learned by visual prompt learning through the lens of property inference and membership inference attacks. Our empirical evaluation shows that the prompts are vulnerable to both attacks. We also demonstrate that the adversary can mount a successful property inference attack with limited cost. Moreover, we show that membership inference attacks against prompts can be successful with relaxed adversarial assumptions. We further make some initial investigations on the defenses and observe that our method can mitigate the membership inference attacks with a decent utility-defense trade-off but fails to defend against property inference attacks. We hope our results can shed light on the privacy risks of the popular prompt learning paradigm. To facilitate the research in this direction, we will share our code and models with the community.

History

Primary Research Area

  • Trustworthy Information Processing

Name of Conference

Usenix Security Symposium (USENIX-Security)

Journal

USENIX Security Symposium (USENIX Security)

Publisher

USENIX

BibTeX

@conference{Wu:Wen:Backes:Berrang:Humbert:Shen:Zhang:2024, title = "Quantifying Privacy Risks of Prompts in Visual Prompt Learning", author = "Wu, Yixin" AND "Wen, R" AND "Backes, M" AND "Berrang, Pascal" AND "Humbert, Mathias" AND "Shen, Yun" AND "Zhang, yang", year = 2024, month = 2, journal = "USENIX Security Symposium (USENIX Security)", publisher = "USENIX" }

Usage metrics

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC