SaTC: CORE: Small: Multi-Party High-dimensional Machine Learning with Privacy

SaTC：核心：小型：具有隐私性的多方高维机器学习

• 批准号: 1717950
• 负责人: David Evans
• 金额: $ 49.86万
• 依托单位: University of Virginia Main Campus
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-01 至 2021-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1717950&HistoricalAwards=false
• 关键词: SaTC; CORE; Small; Multi; Party

Individuals and organizations can frequently benefit from combining their data to learn collective models. However, combining data to enable multi-party learning is often not possible. It may not be permitted due to privacy policies, or may be considered too risky for a business to expose its own data to others. In addition, high-dimensional data are prevalent in modern data-driven applications. Learning from high-dimensional data owned by differential organizations is even more challenging, due to the bias introduced by the high-dimensional machine learning methods. The overarching goal of this project is to address these challenges by developing methods that enable a group of mutually distrusting parties to securely collaborate to apply high dimensional machine learning methods to produce a joint model without exposing their own data. This project enables owners of sensitive data to jointly learn models across their datasets without exposing that data and providing meaningful privacy guarantees. It produces open source software tools and has many important societal applications, including its use in analyzing electronic health records across multiple hospitals to identify medical correlations what could not be found by any individual hospital. The key of multi-party high-dimensional machine learning is to find an efficient way to produce an accurate aggregate model that reflects all of the data, by combining local models that are developed independently based on individual data sets. The strategy of this project is to combine two emerging research directions: distributed machine learning, which seeks to distribute machine learning algorithms across hosts and produce an aggregate model by combining multiple local models; and secure multi-party computation, which enables a group of mutually distrusting parties to jointly compute a function without leaking information about their private inputs or any intermediate results. It also incorporates differential privacy-based mechanisms into multi-party high dimensional learning, which further protects the individual data points in each party. The results of this research have the potential to impact both the machine learning and security research communities. The education plan of this project includes developing open course materials that integrate privacy and machine learning, and provide research-based training opportunities for both undergraduate and graduate students in computer science, systems engineering, and medical informatics. It actively gets underrepresented groups involved in research projects, and trains a new generation of interdisciplinary researchers.

个人和组织通常可以从组合数据来学习集体模型中受益。但是，将数据结合起来启用多方学习通常是不可能的。 由于隐私政策，可能不允许使用它，也可能认为企业无法将自己的数据暴露给其他人。此外，在现代数据驱动的应用程序中，高维数据很普遍。由于高维机器学习方法引入的偏见，从差异组织拥有的高维数据中学习更具挑战性。该项目的总体目标是通过开发使一组相互不信任的各方安全合作以应用高维机器学习方法的方法来解决这些挑战，以在不暴露自己的数据的情况下生成联合模型。该项目使敏感数据的所有者能够在其数据集中共同学习模型，而无需曝光该数据并提供有意义的隐私保证。 它生产开源软件工具并具有许多重要的社会应用，包括用于分析多家医院的电子健康记录以识别任何个人医院无法找到的医学相关性。 多方高维机器学习的关键是找到一种有效的方法来产生一种准确的聚合模型，该模型通过结合基于单个数据集独立开发的本地模型来反映所有数据。该项目的策略是结合两个新兴的研究方向：分布式机器学习，该研究旨在在主机上分发机器学习算法，并通过结合多个本地模型来生成汇总模型；并确保多方计算，这使一组相互不信任的当事方能够共同计算功能，而无需泄漏有关其私人输入或任何中间结果的信息。它还将基于差异隐私的机制纳入多方高维学习中，从而进一步保护各方的各个数据点。这项研究的结果有可能影响机器学习和安全研究社区。该项目的教育计划包括开发开放课程材料，以整合隐私和机器学习，并为计算机科学，系统工程和医学信息学领域的本科生和研究生提供基于研究的培训机会。它积极地使人为不足的团体参与研究项目，并培训了新一代的跨学科研究人员。

项目成果

A Knowledge Transfer Framework for Differentially Private Sparse Learning

• DOI: 10.1609/aaai.v34i04.6090
• 发表时间: 2019-09
• 期刊: ArXiv
• 作者: Lingxiao Wang;Quanquan Gu

Formalizing Distribution Inference Risks

形式化分布推理风险

• 发表时间: 2021
• 期刊: Workshop on Theory and Practice of Differential Privacy
• 作者: Suri, Anshuman;Evans, David
• 通讯作者: Evans, David

Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models

• 发表时间: 2020-03
• 作者: Xiao Zhang;Jinghui Chen;Quanquan Gu;David Evans

RayS: A Ray Searching Method for Hard-label Adversarial Attack

• DOI: 10.1145/3394486.3403225
• 发表时间: 2020-01-01
• 期刊: KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING
• 作者: Chen, Jinghui;Gu, Quanquan
• 通讯作者: Gu, Quanquan

Evaluating Differentially Private Machine Learning in Practice

• 发表时间: 2019-02
• 作者: Bargav Jayaraman;David E. Evans