SaTC: CORE: Small: Auditing Private Statistical and Machine Learning Algorithms: Theory and Practice

SaTC：核心：小型：审计私人统计和机器学习算法：理论与实践

• 批准号: 2247484
• 负责人: Alina Oprea
• 金额: $ 60万
• 依托单位: Northeastern 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 2026-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2247484&HistoricalAwards=false
• 关键词: SaTC; CORE; Small; Auditing; Private

The use of statistics and machine learning to analyze sensitive data poses serious privacy risks to users who contribute their data to these algorithms, including: data reconstruction (revealing large portions of the training data), membership inference (revealing the presence of specific individuals in the training data), and data memorization (revealing specific training examples). Differential privacy has now become the standard for protecting data privacy in machine learning and statistics, as it offers a strong, formal, and quantitative guarantee of individual privacy. However, for many deployments of differential privacy there remains a significant gap between the formal guarantees and expectations in practice, and this project aims to bridge this gap by auditing deployed algorithms to discover and explain their privacy properties. The project’s novelties are building the theoretical foundations of privacy auditing and designing empirical methods that measure the privacy leakage of private algorithms in real-world scenarios. The project’s broader significance and importance will be in specific recommendations to practitioners on choice and use of private algorithms, and an understanding of the potential privacy violations for specific machine learning applications. The project team has expertise in differential privacy, machine learning, and cybersecurity, and plans a set of education tasks and outreach activities: public course materials on trustworthy machine learning and privacy, mentoring undergraduate and graduate students in research projects, and collaboration with industry partners. This project includes three interconnected thrusts addressing different aspects of privacy auditing. The first thrust lays the theoretical foundation of privacy auditing by developing optimal membership inference attacks with stronger guarantees than previous work. The second thrust introduces novel methods for auditing convex machine learning models and neural networks, by using insights from poisoning attacks developed in adversarial machine learning. The final thrust designs tools for auditing end-to-end privacy leakage of machine learning models trained under the continual-learning paradigm. These research thrusts enable a suite of techniques for auditing private algorithms, with the goal of providing guidance to practitioners on how to select private algorithms and their parameters to balance the utility and privacy guarantees on tasks of interest.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.

使用统计学和机器学习来分析敏感数据会给将数据贡献给这些算法的用户带来严重的隐私风险，包括：数据重建（揭示大部分训练数据），成员推断（揭示训练数据中特定个体的存在）和数据记忆（揭示特定训练示例）。差分隐私现已成为机器学习和统计中保护数据隐私的标准，因为它为个人隐私提供了强有力的，正式的和定量的保证。然而，对于许多差异隐私的部署，在实践中的正式保证和期望之间仍然存在显着的差距，本项目旨在通过审计部署的算法来发现和解释其隐私属性来弥合这一差距。 该项目的创新之处在于建立了隐私审计的理论基础，并设计了实证方法来衡量真实世界场景中私有算法的隐私泄露。该项目更广泛的意义和重要性将在于向从业者提供关于选择和使用私有算法的具体建议，以及了解特定机器学习应用程序的潜在隐私侵犯行为。该项目团队拥有差分隐私、机器学习和网络安全方面的专业知识，并计划了一系列教育任务和推广活动：关于值得信赖的机器学习和隐私的公共课程材料，指导研究项目中的本科生和研究生，以及与行业合作伙伴的合作。该项目包括三个相互关联的重点，解决隐私审计的不同方面。第一个推力奠定了隐私审计的理论基础，通过开发最佳的成员推理攻击比以前的工作更强的保证。第二个重点介绍了审计凸机器学习模型和神经网络的新方法，通过使用对抗机器学习中开发的中毒攻击的见解。最后一个推力设计了用于审计在持续学习范式下训练的机器学习模型的端到端隐私泄露的工具。这些研究成果为审计私有算法提供了一套技术，目的是为从业者提供指导，指导他们如何选择私有算法及其参数，以平衡感兴趣任务的实用性和隐私保证。该奖项反映了NSF的法定使命，并被认为值得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来支持。

项目成果

Differentially Private Medians and Interior Points for Non-Pathological Data

• DOI: 10.48550/arxiv.2305.13440
• 发表时间: 2023-05
• 期刊: ArXiv
• 作者: M. Aliakbarpour;Rose Silver;T. Steinke;Jonathan Ullman

Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning

• DOI: 10.48550/arxiv.2310.03838
• 发表时间: 2023-10
• 期刊: ArXiv
• 作者: Harsh Chaudhari;Giorgio Severi;Alina Oprea;Jonathan R. Ullman