CAREER: Exact Optimal and Data-Adaptive Algorithms and Tools for Differential Privacy

职业：用于差异隐私的精确最优和数据自适应算法和工具

• 批准号: 2048091
• 负责人: Yu-Xiang Wang
• 金额: $ 49.92万
• 依托单位: University of California-Santa Barbara
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-03-15 至 2026-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2048091&HistoricalAwards=false
• 关键词: CAREER; Exact; Optimal; Data; Adaptive

This project is motivated by the increasing public concerns on privacy issues, new legislations and the high demand for privacy enhancing technologies such as differential privacy (DP) in applications from both private and public sectors. The overarching theme of the project is to address the pressing new challenges that arise as differential privacy transforms from a theoretical construct into a practical technology. The project advances the state-of-the-art of research in the area of DP, and contributes to privacy education. On the research front, the project develops new algorithms and analytical tools that enable more precise privacy accounting and higher utility in DP. On the education front, the project involves training future leaders in DP areas, creating educational materials and expanding an open-source software library called autodp that makes state-of-the-art differentially private computation more accessible. Collectively, the integrated research and educational activities contribute to ongoing collaborative efforts in building innovative applications of differential privacy. The project has three main components in use-inspired fundamental research. The first component unifies the recent breakthroughs in DP, such as, Renyi DP, moments accountant, f-DP and produce an intermediate functional representation that allows lossless conversions among these representations. The second component focuses on investigating the stronger privacy properties permitted by the structures of the actual data, and addressing the dilemma of interpreting worst-case privacy on average-case data. The third component focuses on using a public dataset to ``denoise'' the private data releases or to facilitate private machine learning. The outputs of the research will be broadly shared through integration in autodp library, and will be integrated in courses.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

这个项目的动机是公众对隐私问题的日益关注，新的立法，以及私营和公共部门的应用程序对隐私增强技术(如差异隐私(DP))的高度需求。该项目的首要主题是解决差异隐私从理论构建转化为实用技术时出现的紧迫新挑战。该项目推进了DP领域最先进的研究，并为隐私教育做出了贡献。在研究方面，该项目开发了新的算法和分析工具，使DP能够实现更精确的隐私核算和更高的效用。在教育方面，该项目包括在DP领域培训未来的领导者，创建教育材料，并扩大一个名为AutoDp的开放源码软件库，使最先进的差异私人计算更容易获得。总体而言，综合研究和教育活动有助于在构建差异隐私的创新应用方面进行持续的合作努力。该项目在受使用启发的基础研究中有三个主要组成部分。第一个组件统一了DP中最近的突破，如Renyi DP、Moments Account、f-DP，并产生了允许在这些表示之间进行无损转换的中间泛函表示。第二部分侧重于调查实际数据的结构所允许的更强的隐私属性，并解决解释平均情况数据的最坏情况隐私的两难问题。第三个组件侧重于使用公共数据集对私有数据发布进行“去噪”或促进私有机器学习。这项研究的成果将通过整合在AUTODP图书馆中广泛共享，并将在课程中整合。这一奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Differentially Private Linear Sketches: Efficient Implementations and Applications

差分私有线性草图：高效的实现和应用

• 发表时间: 2022
• 期刊: Advances in neural information processing systems
• 作者: Zhao, Fuheng;Qiao, Dan;Redberg, Rachel;Agrawal, Divyakant;Abbadi, Amr El;Wang, Yu-Xiang
• 通讯作者: Wang, Yu-Xiang

SeqPATE: Differentially Private Text Generation via Knowledge Distillation

• 发表时间: 2022
• 作者: Zhiliang Tian;Ying Zhao;Ziyue Huang;Yu-Xiang Wang;N. Zhang;He He-He

Near-Optimal Differentially Private Reinforcement Learning

• DOI: 10.48550/arxiv.2212.04680
• 发表时间: 2022-12
• 期刊: ArXiv
• 作者: Dan Qiao;Yu-Xiang Wang

Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment

推进差异化隐私：现实世界部署的现状和未来方向

• DOI: 10.1162/99608f92.d3197524
• 发表时间: 2024
• 期刊: Harvard data science review
• 作者: Cummings, Rachel;Desfontaines, Damien;Evans, David;Geambasu, Roxana;Huang, Yangsibo;Jagielski, Matthew;Kairouz, Peter;Kamath, Gautam;Oh, Sewoong;Ohrimenko, Olga
• 通讯作者: Ohrimenko, Olga

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners

• DOI: 10.48550/arxiv.2401.00583
• 发表时间: 2023-12
• 期刊: ArXiv
• 作者: Rachel Redberg;Antti Koskela;Yu-Xiang Wang