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 2108.04417cs.LGcs.AIcs.CR
收藏

隐私保护机器学习:方法、挑战和方向

Privacy-Preserving Machine Learning: Methods, Challenges and Directions

IBM Research - Almaden Research Center(IBM研究院阿尔马登研究中心);School of Computing and Information, University of Pittsburgh(匹兹堡大学计算与信息学院)

Runhua Xu, Nathalie Baracaldo, James Joshi

摘要:

机器学习(ML)越来越多地被广泛应用于各种应用领域。通常,性能良好的ML模型依赖于大量的训练数据和高性能的计算资源。由于高度隐私敏感信息泄露的潜在风险,这种对大量数据的需求和使用引发了严重的隐私问题;此外,不断变化的监管环境越来越多地限制对隐私敏感数据的访问和使用,这给充分受益于ML的数据驱动应用带来了重大挑战。经过训练的ML模型也可能容易受到对抗攻击,例如成员关系、属性或属性推断攻击以及模型反演攻击。因此,许多新兴应用迫切需要设计良好的隐私保护ML(PPML)解决方案。越来越多的来自学术界和工业界的重要研究工作可以在PPML领域看到,这些领域旨在将隐私保护技术集成到ML管道或特定算法中,或者设计各种PPML架构。特别是,现有的PPML研究横切ML,系统和应用程序设计,以及安全和隐私领域;因此,迫切需要了解最先进的研究,相关的挑战和PPML领域未来研究的研究路线图。在本文中,我们系统地回顾和总结现有的隐私保护方法,并提出了一个阶段,保证,和效用(PGU)三元组为基础的模型来理解和指导各种PPML解决方案的评估分解其隐私保护功能。我们讨论了PPML的独特特征和挑战,并概述了可能的研究方向,这些方向可以利用并使多个研究社区受益,如ML,分布式系统,安全性和隐私。

英文摘要:

Machine learning (ML) is increasingly being adopted in a wide variety of application domains. Usually, a well-performing ML model relies on a large volume of training data and high-powered computational resources. Such a need for and the use of huge volumes of data raise serious privacy concerns because of the potential risks of leakage of highly privacy-sensitive information; further, the evolving regulatory environments that increasingly restrict access to and use of privacy-sensitive data add significant challenges to fully benefiting from the power of ML for data-driven applications. A trained ML model may also be vulnerable to adversarial attacks such as membership, attribute, or property inference attacks and model inversion attacks. Hence, well-designed privacy-preserving ML (PPML) solutions are critically needed for many emerging applications. Increasingly, significant research efforts from both academia and industry can be seen in PPML areas that aim toward integrating privacy-preserving techniques into ML pipeline or specific algorithms, or designing various PPML architectures. In particular, existing PPML research cross-cut ML, systems and applications design, as well as security and privacy areas; hence, there is a critical need to understand state-of-the-art research, related challenges and a research roadmap for future research in PPML area. In this paper, we systematically review and summarize existing privacy-preserving approaches and propose a Phase, Guarantee, and Utility (PGU) triad based model to understand and guide the evaluation of various PPML solutions by decomposing their privacy-preserving functionalities. We discuss the unique characteristics and challenges of PPML and outline possible research directions that leverage as well as benefit multiple research communities such as ML, distributed systems, security and privacy.

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。

↑