EAGER: Bridging The Gap between Theory and Practice in Data Privacy

EAGER：弥合数据隐私理论与实践之间的差距

• 批准号: 1640374
• 负责人: Ninghui Li
• 金额: $ 29.96万
• 依托单位: Purdue University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-09-01 至 2020-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1640374&HistoricalAwards=false
• 关键词: EAGER; Bridging; Gap; between; Theory

This project aims to bridge the gap between theory and practice in privacy-preserving data sharing and analysis. Data collected by organizations and agencies are a key resource in today's information age. However, the disclosure of those data poses serious threats to individual privacy. While differential privacy provides a solid foundation for developing techniques to balance privacy and utility in data sharing, currently there is a significant gap between theory and practice in research in this area. In the current state of the art, each task requires specialized algorithms to achieve acceptable trade-off of privacy and utility. The process of designing new algorithms is manual and challenging. Furthermore, research in this area tends to take either a pure theoretical approach or a pure experimental approach; both have significant limitations. This project aims to develop algorithms that can be broadly and automatically applied, and methodologies for combining theoretical analysis with experimental validations, focusing on concrete (instead of asymptotic) analysis where constants are spelled out. Advances in data privacy techniques will benefit society by providing a better balance between the need to release data to serve public interest and the need to protect individuals' privacy. The project pursues the following research goals to advance the state-of-the-art of data privacy. One goal is to develop a general method that can take a non-private data analysis algorithm as a blackbox, and make it private. This may require the development of a data privacy notion that is more relaxed than differential privacy. Another goal is to develop a concrete approach to understanding the utility of data analysis algorithms. The theoretical approach of proving asymptotic utility bounds is limited for a number of reasons. Asymptotic analysis ignores constants (and oftentimes poly-logarithmic terms as well), which are critical for utility in practice. A method with an appealing asymptotic utility bound often performs poorly except for very large parameters, when applying the method requires an unacceptable amount of space and time computing resources. As the utility bound must hold for all datasets (including pathological ones), such bounds can be so loose that they are meaningless once the actual parameters are plugged in. Bridging this gap requires better understanding of the factors affecting utility, better utility metrics, and methods to formalize the dependencies of utility on dataset features. The resulting concrete approach combines theoretical analysis with heuristic approximations and experimental validations, and can more effectively guide the development of practically effective algorithms.

该项目旨在弥合隐私保护数据共享和分析理论与实践之间的差距。各组织和机构收集的数据是当今信息时代的关键资源。 然而，这些数据的披露对个人隐私构成严重威胁。 虽然差异隐私为开发在数据共享中平衡隐私和实用性的技术提供了坚实的基础，但目前在这一领域的研究中理论和实践之间存在显着差距。 在现有技术中，每个任务都需要专门的算法来实现隐私和实用性的可接受的权衡。 设计新算法的过程是手动的，具有挑战性。 此外，这一领域的研究往往采取纯理论方法或纯实验方法;两者都有很大的局限性。 该项目旨在开发可以广泛自动应用的算法，以及将理论分析与实验验证相结合的方法，重点是具体的（而不是渐进的）分析，其中常数被阐明。 数据隐私技术的进步将使社会受益，因为它在为公共利益发布数据的需要与保护个人隐私的需要之间提供了更好的平衡。 该项目追求以下研究目标，以推进最先进的数据隐私技术。 一个目标是开发一种通用的方法，可以将非私有数据分析算法作为黑盒，并使其私有化。 这可能需要制定一个比差别隐私更宽松的数据隐私概念。 另一个目标是开发一种具体的方法来理解数据分析算法的实用性。 证明渐近效用界的理论方法是有限的，原因有很多。 渐近分析忽略了常数（通常也忽略了多对数项），这些常数在实践中对实用性至关重要。 一个有吸引力的渐近效用界的方法通常表现不佳，除了非常大的参数，当应用该方法需要不可接受的空间和时间的计算资源。 由于效用界限必须适用于所有数据集（包括病理数据集），因此这些界限可能非常松散，一旦插入实际参数，它们就毫无意义。 弥合这一差距需要更好地理解影响效用的因素，更好的效用度量，以及将效用对数据集特征的依赖性形式化的方法。 由此产生的具体方法结合了理论分析与启发式近似和实验验证，可以更有效地指导实际有效的算法的发展。

项目成果

CALM: Consistent Adaptive Local Marginal for Marginal Release under Local Differential Privacy

• DOI: 10.1145/3243734.3243742
• 发表时间: 2018-10
• 期刊: Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security
• 作者: Zhikun Zhang;Tianhao Wang;Ninghui Li;Shibo He;Jiming Chen

Answering Multi-Dimensional Analytical Queries under Local Differential Privacy

• DOI: 10.1145/3299869.3319891
• 发表时间: 2019-06
• 期刊: Proceedings of the 2019 International Conference on Management of Data
• 作者: Tianhao Wang;Bolin Ding;Jingren Zhou;Cheng Hong;Zhicong Huang;Ninghui Li;S. Jha

Locally Differentially Private Protocols for Frequency Estimation

• 发表时间: 2017-08
• 作者: Tianhao Wang;Jeremiah Blocki;Ninghui Li;S. Jha

Understanding the Sparse Vector Technique for Differential Privacy

• DOI: 10.14778/3055330.3055331
• 发表时间: 2017-02-01
• 期刊: PROCEEDINGS OF THE VLDB ENDOWMENT
• 影响因子: 2.5
• 作者: Lyu, Min;Su, Dong;Li, Ninghui
• 通讯作者: Li, Ninghui

Locally Differentially Private Frequency Estimation with Consistency

• DOI: 10.14722/ndss.2020.24157
• 发表时间: 2019-05
• 期刊: Proceedings 2020 Network and Distributed System Security Symposium
• 作者: Tianhao Wang;Milan Lopuhaä-Zwakenberg;Zitao Li;B. Škorić;Ninghui Li