arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.12254cs.LGcs.CRstat.ML
收藏

深度学习中的隐私问题研究综述

Privacy in Deep Learning: A Survey

University of California San Diego(加州大学圣地亚哥分校);Massachusetts Institute of Technology(麻省理工学院)

Fatemehsadat Mireshghallah, Mohammadkazem Taram, Praneeth Vepakomma, Abhishek Singh, Ramesh Raskar, Hadi Esmaeilzadeh

摘要:

深度学习在包括视觉、推荐系统、自然语言处理等在内的许多领域的不断发展,已经导致在生产系统中采用深度神经网络(DNN)。大型数据集的可用性和高计算能力是这些进步的主要贡献者。数据集通常是众包的,可能包含敏感信息。这造成了严重的隐私问题,因为这些数据可能会被滥用或通过各种漏洞泄露。即使云提供商和通信链路是可信的,仍然存在推理攻击的威胁,攻击者可以推测用于训练的数据的属性,或者找到底层模型架构和参数。在本次调查中,我们回顾了深度学习带来的隐私问题,以及为解决这些问题而引入的缓解技术。我们还表明,在文献中有一个差距,关于测试时推理隐私,并提出了未来可能的研究方向。

英文摘要:

The ever-growing advances of deep learning in many areas including vision, recommendation systems, natural language processing, etc., have led to the adoption of Deep Neural Networks (DNNs) in production systems. The availability of large datasets and high computational power are the main contributors to these advances. The datasets are usually crowdsourced and may contain sensitive information. This poses serious privacy concerns as this data can be misused or leaked through various vulnerabilities. Even if the cloud provider and the communication link is trusted, there are still threats of inference attacks where an attacker could speculate properties of the data used for training, or find the underlying model architecture and parameters. In this survey, we review the privacy concerns brought by deep learning, and the mitigating techniques introduced to tackle these issues. We also show that there is a gap in the literature regarding test-time inference privacy, and propose possible future research directions.

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。

↑