Collaborative Research: CIF: Medium: Fundamental Limits of Privacy-Enhancing Technologies

合作研究：CIF：中：隐私增强技术的基本限制

• 批准号: 2312666
• 负责人: Oliver Kosut
• 金额: $ 76.42万
• 依托单位: Arizona State University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-10-01 至 2027-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2312666&HistoricalAwards=false
• 关键词: Collaborative; Research; CIF; Medium; Fundamental

Balancing the preservation of individual privacy and the utility of aggregate data for societal benefit is crucial in the modern data-driven world. In fields such as healthcare, education, and resource allocation, the responsible use of personal data can bring transformative changes and fuel the development of privacy- and fairness-guaranteed machine learning and artificial intelligence algorithms. This project aims to improve privacy-enhancing technologies (PETs) that uphold individual privacy while allowing comprehensive data analysis. The research will result in new methods that optimize PETs for privacy while minimizing their hidden and apparent costs, such as distortion and bias. Moreover, this project will also develop new methods for generating synthetic yet realistic data with privacy safeguards. Ultimately, this research will result in PETs that are more private, accurate, and fair. In practice, these improvements can impact a range of machine learning applications in industry, healthcare, and government. The project also promotes inclusivity by engaging diverse students through research internships and STEM events.The research is divided into four interconnected areas, each tackling a distinct aspect of PETs that ensure differential privacy (DP). The first area develops optimal privacy mechanisms, specifically for applications that require a large number of data processing steps, such as gradient descent-based training algorithms used in machine learning. The second area of focus is enhancing privacy accounting, aiming to derive accurate and computationally tractable methods that track DP guarantees using tools from information theory. The third area assesses the costs of privacy, scrutinizing not just the impact of DP on accuracy, but also fairness and arbitrariness in machine learning models trained with DP-ensuring algorithms. The final focus is on generating realistic synthetic data, which, while maintaining privacy, can be used for various statistical tasks. The project employs a diverse range of techniques from information theory, optimization, mathematical physics, and machine learning.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.

在现代数据驱动的世界中，平衡个人隐私的保护和聚合数据对社会效益的利用至关重要。在医疗保健、教育和资源分配等领域，负责任地使用个人数据可以带来革命性的变化，并推动隐私和公平保证的机器学习和人工智能算法的发展。该项目旨在改进隐私增强技术（PET），在保护个人隐私的同时允许进行全面的数据分析。该研究将产生新方法，优化 PET 的隐私性，同时最大限度地减少其隐藏和明显的成本，例如失真和偏见。此外，该项目还将开发新方法来生成具有隐私保护的合成且真实的数据。最终，这项研究将使 PET 更加私密、准确和公平。实际上，这些改进可能会影响工业、医疗保健和政府中的一系列机器学习应用。该项目还通过研究实习和 STEM 活动吸引不同的学生来促进包容性。该研究分为四个相互关联的领域，每个领域都解决 PET 的一个独特方面，以确保差异隐私 (DP)。第一个领域开发最佳隐私机制，特别是针对需要大量数据处理步骤的应用程序，例如机器学习中使用的基于梯度下降的训练算法。第二个重点领域是加强隐私核算，旨在使用信息论工具导出准确且易于计算处理的方法来跟踪 DP 保证。第三个领域评估隐私成本，不仅审查 DP 对准确性的影响，还审查使用 DP 确保算法训练的机器学习模型的公平性和任意性。最后的重点是生成真实的合成数据，在保持隐私的同时，可用于各种统计任务。该项目采用了信息论、优化、数学物理和机器学习等多种技术。该奖项反映了 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

An Operational Approach to Information Leakage via Generalized Gain Functions

通过广义增益函数处理信息泄漏的操作方法

• DOI: 10.1109/tit.2023.3341148
• 发表时间: 2024-02
• 期刊: IEEE Transactions on Information Theory
• 影响因子: 2.5
• 作者: Kurri, Gowtham R.;Sankar, Lalitha;Kosut, Oliver
• 通讯作者: Kosut, Oliver