Collaborative Research: SaTC: CORE: Small: Foundations for the Next Generation of Private Learning Systems

协作研究:SaTC:核心:小型:下一代私人学习系统的基础

基本信息

  • 批准号:
    2120611
  • 负责人:
  • 金额:
    $ 10万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2021
  • 资助国家:
    美国
  • 起止时间:
    2021-10-01 至 2023-09-30
  • 项目状态:
    已结题

项目摘要

Recent advances in large-scale machine learning (ML) promise a range of benefits to society, but also introduce new risks. One major risk is a loss of privacy for the individuals whose data powers the machine learning algorithms. There are now convincing demonstrations that algorithms for machine learning can reveal sensitive information about individuals in their training data by memorizing specific strings of sensitive text such as bank account numbers or through membership-inference attacks. In the recent years, a framework called differential privacy---a mathematically principled, quantitative notion of what it means for an algorithm to ensure privacy for the individuals who contribute training data---has led to significant progress towards privacy in machine learning. This progress offers a proof-of-concept that we can hope to enjoy some of the benefits of using machine learning on sensitive data, while measuring and limiting breaches of confidentiality. This project will investigate and begin to make some of the fundamental advances that are necessary to make differentially private ML a viable technology. The focus will be on laying the groundwork for differentially private ML for entire systems, rather than for standalone tasks, which have been the focus of prior work. This project team comprising researchers with a broad range of expertise in ML, algorithms, systems, and cybersecurity, has planned a set of education tasks: public-facing set of course materials on differentially private machine learning and statistics and and an undergraduate-level textbook on differential privacy.This project includes three technical thrusts that will lay the groundwork for future efforts to build private ML systems. The first thrust will be to improve the foundational algorithms that enable differentially private ML on high-dimensional data. The second thrust will be to build a bridge between algorithms for standalone ML tasks and algorithms for systems-level workloads of ML tasks, by developing differentially private algorithms for training many personalized models, which is a paradigmatic workload in ML. The final thrust will consist of empirical work on auditing differentially private ML methods to understand how the real-world privacy costs compare to those predicted by the theory of differential privacy when these algorithms are used as part of realistic workloads, such as models that are continually updated with new data. This privacy auditing will also facilitate detecting unwanted memorization of training data in machine learning, and also provide more quantitative approaches to auditing differentially private algorithms based on membership-inference and data poisoning.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.
大规模机器学习(ML)的最新进展给社会带来了一系列好处,但也带来了新的风险。一大风险是个人隐私的丧失,这些个人的数据为机器学习算法提供动力。现在有令人信服的演示表明,机器学习的算法可以通过记忆特定的敏感文本字符串,如银行账号,或通过成员资格推理攻击,在他们的训练数据中揭示关于个人的敏感信息。近年来,一个被称为差异隐私的框架-一个数学上有原则的、定量的概念,说明了算法确保提供训练数据的个人的隐私意味着什么-导致了机器学习中在隐私方面的重大进展。这一进展提供了一个概念证明,我们可以希望享受在敏感数据上使用机器学习的一些好处,同时衡量和限制违反保密性的行为。这个项目将研究并开始取得一些基本的进步,这些进步是使不同的私有ML成为可行的技术所必需的。重点将是为整个系统的不同私有ML奠定基础,而不是为之前的工作重点--独立任务--奠定基础。这个项目团队由在ML、算法、系统和网络安全方面拥有广泛专业知识的研究人员组成,计划了一套教育任务:面向公众的一套关于不同私人机器学习和统计学的课程材料,以及一本关于差异私人的本科生水平教科书。该项目包括三个技术推动力,将为未来建立私人ML系统的努力奠定基础。第一个推力将是改进基础算法,使高维数据上的差异私有ML成为可能。第二个推动力将是通过开发用于训练许多个性化模型的不同私有算法,在独立ML任务的算法和ML任务的系统级工作负载的算法之间建立一座桥梁,这是ML中的一个范例工作负载。最后的重点将包括审计差异私有ML方法的经验工作,以了解当这些算法用作现实工作负载的一部分时,现实世界的隐私成本与差异隐私理论预测的成本相比如何,例如使用新数据不断更新的模型。这种隐私审计还将有助于在机器学习中检测不必要的训练数据记忆,并提供更多量化方法来审计基于成员推理和数据中毒的不同私有算法。该奖项反映了NSF的法定使命,并通过使用基金会的智力优势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

期刊论文数量(11)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Private Data Stream Analysis for Universal Symmetric Norm Estimation
用于通用对称范数估计的私有数据流分析
Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints
布朗降噪:在精度约束下最大化隐私
Nonparametric Extensions of Randomized Response for Private Confidence Sets
  • DOI:
  • 发表时间:
    2022-02
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Ian Waudby-Smith;Zhiwei Steven Wu;Aaditya Ramdas
  • 通讯作者:
    Ian Waudby-Smith;Zhiwei Steven Wu;Aaditya Ramdas
On Privacy and Personalization in Cross-Silo Federated Learning
  • DOI:
    10.48550/arxiv.2206.07902
  • 发表时间:
    2022-06
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Ziyu Liu;Shengyuan Hu;Zhiwei Steven Wu;Virginia Smith
  • 通讯作者:
    Ziyu Liu;Shengyuan Hu;Zhiwei Steven Wu;Virginia Smith
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning
  • DOI:
  • 发表时间:
    2022-02
  • 期刊:
  • 影响因子:
    0
  • 作者:
    A. Bietti;Chen-Yu Wei;Miroslav Dudík;J. Langford;Zhiwei Steven Wu
  • 通讯作者:
    A. Bietti;Chen-Yu Wei;Miroslav Dudík;J. Langford;Zhiwei Steven Wu
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Zhiwei Steven Wu其他文献

Logarithmic Query Complexity for Approximate Nash Computation in Large Games
大型游戏中近似纳什计算的对数查询复杂度
  • DOI:
  • 发表时间:
    2016
  • 期刊:
  • 影响因子:
    0.5
  • 作者:
    P. Goldberg;Francisco Javier Marmolejo;Zhiwei Steven Wu
  • 通讯作者:
    Zhiwei Steven Wu
Competing Bandits: The Perils of Exploration Under Competition
强盗竞争:竞争中探索的危险
  • DOI:
  • 发表时间:
    2019
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Guy Aridor;Y. Mansour;Aleksandrs Slivkins;Zhiwei Steven Wu
  • 通讯作者:
    Zhiwei Steven Wu
Inducing Approximately Optimal Flow Using Truthful Mediators
使用真实的中介者诱导近似最佳的流动
Provable Multi-Party Reinforcement Learning with Diverse Human Feedback
可证明的多方强化学习与不同的人类反馈
  • DOI:
    10.48550/arxiv.2403.05006
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Huiying Zhong;Zhun Deng;Weijie J. Su;Zhiwei Steven Wu;Linjun Zhang
  • 通讯作者:
    Linjun Zhang
Membership Inference Attacks on Diffusion Models via Quantile Regression
通过分位数回归对扩散模型进行成员推理攻击
  • DOI:
    10.48550/arxiv.2312.05140
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Shuai Tang;Zhiwei Steven Wu;Sergül Aydöre;Michael Kearns;Aaron Roth
  • 通讯作者:
    Aaron Roth

Zhiwei Steven Wu的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Zhiwei Steven Wu', 18)}}的其他基金

CAREER: New Frontiers of Private Learning and Synthetic Data
职业:私人学习和合成数据的新领域
  • 批准号:
    2339775
  • 财政年份:
    2024
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Collaborative Research: SaTC: CORE: Medium: Private Model Personalization
协作研究:SaTC:核心:媒介:私人模型个性化
  • 批准号:
    2232693
  • 财政年份:
    2023
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
FAI: Advancing Fairness in AI with Human-Algorithm Collaborations
FAI:通过人类算法合作促进人工智能的公平性
  • 批准号:
    2125692
  • 财政年份:
    2020
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
FAI: Advancing Fairness in AI with Human-Algorithm Collaborations
FAI:通过人类算法合作促进人工智能的公平性
  • 批准号:
    1939606
  • 财政年份:
    2020
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant

相似国自然基金

Research on Quantum Field Theory without a Lagrangian Description
  • 批准号:
    24ZR1403900
  • 批准年份:
    2024
  • 资助金额:
    0.0 万元
  • 项目类别:
    省市级项目
Cell Research
  • 批准号:
    31224802
  • 批准年份:
    2012
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Cell Research
  • 批准号:
    31024804
  • 批准年份:
    2010
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Cell Research (细胞研究)
  • 批准号:
    30824808
  • 批准年份:
    2008
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Research on the Rapid Growth Mechanism of KDP Crystal
  • 批准号:
    10774081
  • 批准年份:
    2007
  • 资助金额:
    45.0 万元
  • 项目类别:
    面上项目

相似海外基金

Collaborative Research: SaTC: CORE: Medium: Using Intelligent Conversational Agents to Empower Adolescents to be Resilient Against Cybergrooming
合作研究:SaTC:核心:中:使用智能会话代理使青少年能够抵御网络诱骗
  • 批准号:
    2330940
  • 财政年份:
    2024
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Collaborative Research: SaTC: CORE: Medium: Differentially Private SQL with flexible privacy modeling, machine-checked system design, and accuracy optimization
协作研究:SaTC:核心:中:具有灵活隐私建模、机器检查系统设计和准确性优化的差异化私有 SQL
  • 批准号:
    2317232
  • 财政年份:
    2024
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Collaborative Research: NSF-BSF: SaTC: CORE: Small: Detecting malware with machine learning models efficiently and reliably
协作研究:NSF-BSF:SaTC:核心:小型:利用机器学习模型高效可靠地检测恶意软件
  • 批准号:
    2338301
  • 财政年份:
    2024
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Collaborative Research: SaTC: CORE: Medium: Differentially Private SQL with flexible privacy modeling, machine-checked system design, and accuracy optimization
协作研究:SaTC:核心:中:具有灵活隐私建模、机器检查系统设计和准确性优化的差异化私有 SQL
  • 批准号:
    2317233
  • 财政年份:
    2024
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Collaborative Research: NSF-BSF: SaTC: CORE: Small: Detecting malware with machine learning models efficiently and reliably
协作研究:NSF-BSF:SaTC:核心:小型:利用机器学习模型高效可靠地检测恶意软件
  • 批准号:
    2338302
  • 财政年份:
    2024
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Collaborative Research: SaTC: CORE: Medium: Using Intelligent Conversational Agents to Empower Adolescents to be Resilient Against Cybergrooming
合作研究:SaTC:核心:中:使用智能会话代理使青少年能够抵御网络诱骗
  • 批准号:
    2330941
  • 财政年份:
    2024
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Collaborative Research: SaTC: CORE: Small: Towards Secure and Trustworthy Tree Models
协作研究:SaTC:核心:小型:迈向安全可信的树模型
  • 批准号:
    2413046
  • 财政年份:
    2024
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
Collaborative Research: SaTC: EDU: RoCCeM: Bringing Robotics, Cybersecurity and Computer Science to the Middled School Classroom
合作研究:SaTC:EDU:RoCCeM:将机器人、网络安全和计算机科学带入中学课堂
  • 批准号:
    2312057
  • 财政年份:
    2023
  • 资助金额:
    $ 10万
  • 项目类别:
    Standard Grant
Collaborative Research: SaTC: CORE: Small: Investigation of Naming Space Hijacking Threat and Its Defense
协作研究:SaTC:核心:小型:命名空间劫持威胁及其防御的调查
  • 批准号:
    2317830
  • 财政年份:
    2023
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
Collaborative Research: SaTC: CORE: Small: Towards a Privacy-Preserving Framework for Research on Private, Encrypted Social Networks
协作研究:SaTC:核心:小型:针对私有加密社交网络研究的隐私保护框架
  • 批准号:
    2318843
  • 财政年份:
    2023
  • 资助金额:
    $ 10万
  • 项目类别:
    Continuing Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了