arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.06112cs.CRcs.AIcs.ITcs.LGmath.ITmath.OC
收藏

模特隐私的信息清洗

Information Laundering for Model Privacy

University of Minnesota(明尼苏达大学);University of Utah(犹他大学);Stanford University(斯坦福大学)

Xinran Wang, Yu Xiang, Jun Gao, Jie Ding

摘要:

在这项工作中,我们提出了信息清洗,一个新的框架,以提高模型的隐私。与涉及保护原始数据信息的数据隐私不同,模型隐私旨在保护已学习的模型,该模型将被部署用于公共用途。私有模型可以从一般的学习方法中获得,它的部署意味着它将为给定的输入查询返回确定性或随机响应。信息清洗模型由概率组件组成,这些组件故意操纵对模型的查询的预期输入和输出,因此模型的对抗性获取不太可能。在这个框架下,我们发展了一个信息理论的原则来量化模型效用和隐私泄露之间的基本权衡,并得出最优设计。

英文摘要:

In this work, we propose information laundering, a novel framework for enhancing model privacy. Unlike data privacy that concerns the protection of raw data information, model privacy aims to protect an already-learned model that is to be deployed for public use. The private model can be obtained from general learning methods, and its deployment means that it will return a deterministic or random response for a given input query. An information-laundered model consists of probabilistic components that deliberately maneuver the intended input and output for queries to the model, so the model's adversarial acquisition is less likely. Under the proposed framework, we develop an information-theoretic principle to quantify the fundamental tradeoffs between model utility and privacy leakage and derive the optimal design.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑