Collaborative Research: SaTC: CORE: Medium: Private Model Personalization
协作研究:SaTC:核心:媒介:私人模型个性化
基本信息
- 批准号:2232694
- 负责人:
- 金额:$ 45万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2023
- 资助国家:美国
- 起止时间:2023-04-15 至 2027-03-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Modern machine learning's success has brought with it a serious challenge for privacy: it is now widely documented that the models currently in use encode individual inputs in surprising ways. Understanding how to detect such memorization, and training methods that avoid it, is a major topic of current research. However, prior investigations have focused mostly on the batch model of machine learning, in which training data are all drawn from a single underlying population.This project seeks to understand the privacy risks that arise when the training data from many populations are pooled in order to take advantage of structure that is shared across populations. For example, many individuals’ photos could be pooled to train better face recognition algorithms (even though each person is interested in a different set of faces). Such settings—called “model personalization”, “multitask learning” or “meta-learning”—provide a powerful framework for combining insights from far-flung, disparate data sources. However, their power raises fundamental questions about the extent to which the results of joint analysis violate the privacy of individual users' data. The project looks both at attacks on privacy—methods for extracting individual-level or dataset-level information from the resulting predictions or models—as well as mitigation strategies based on the now-standard, state-of-the-art framework, differential privacy. The project involves both theoretical analysis and real-world experimentation. It will inform the development of training algorithms for these complex settings and provide tools for use by companies and other research groups. This impact will be facilitated by the project team's existing collaborations with industry researchers.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.
现代机器学习的成功给隐私带来了严峻的挑战:目前广泛记录的是,目前使用的模型以令人惊讶的方式编码个人输入。了解如何检测这种记忆,以及如何训练避免这种记忆的方法,是当前研究的一个主要课题。然而,之前的研究主要集中在机器学习的批处理模型上,其中训练数据都是从单个潜在人群中提取的。该项目旨在了解为了利用跨群体共享的结构,将来自许多群体的训练数据汇集在一起时所产生的隐私风险。例如,许多人的照片可以汇集起来训练更好的人脸识别算法(即使每个人对一组不同的面孔感兴趣)。这样的设置——被称为“模型个性化”、“多任务学习”或“元学习”——提供了一个强大的框架,可以将来自遥远的、不同的数据源的见解结合起来。然而,他们的权力引发了一个根本性的问题,即联合分析的结果在多大程度上侵犯了个人用户的数据隐私。该项目着眼于对隐私的攻击——从结果预测或模型中提取个人级或数据集级信息的方法——以及基于现在标准的、最先进的框架——差分隐私的缓解策略。这个项目包括理论分析和现实世界的实验。它将为这些复杂设置的训练算法的开发提供信息,并为公司和其他研究团体提供使用工具。项目团队与行业研究人员的现有合作将促进这种影响。该奖项反映了美国国家科学基金会的法定使命,并通过使用基金会的知识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
期刊论文数量(6)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Counting Distinct Elements in the Turnstile Model with Differential Privacy under Continual Observation
在持续观察下计算具有差异隐私的旋转栅门模型中的不同元素
- DOI:
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Kalemaj, Iden;Jain, Palak;Raskhodnikova, Sofya;Sivakumar, Satchit;Smith, Adam D
- 通讯作者:Smith, Adam D
Node-Differentially Private Estimation of the Number of Connected Components
- DOI:10.1145/3584372.3588671
- 发表时间:2023-04
- 期刊:
- 影响因子:0
- 作者:Iden Kalemaj;Sofya Raskhodnikova;Adam D. Smith;Charalampos E. Tsourakakis
- 通讯作者:Iden Kalemaj;Sofya Raskhodnikova;Adam D. Smith;Charalampos E. Tsourakakis
Fast, Sample-Efficient, Affine-Invariant Private Mean and Covariance Estimation for Subgaussian DistributionsGavin Brown and Samuel B. Hopkins and Adam D. Smith
亚高斯分布的快速、样本高效、仿射不变私有均值和协方差估计Gavin Brown、Samuel B. Hopkins 和 Adam D. Smith
- DOI:
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Brown, Gavin;Hopkins, Samuel B;Smith, Adam D
- 通讯作者:Smith, Adam D
The Price of Differential Privacy under Continual Observation
- DOI:
- 发表时间:2021-12
- 期刊:
- 影响因子:0
- 作者:Palak Jain;Sofya Raskhodnikova;Satchit Sivakumar;Adam D. Smith
- 通讯作者:Palak Jain;Sofya Raskhodnikova;Satchit Sivakumar;Adam D. Smith
Control, Confidentiality, and the Right to be Forgotten
控制、保密和被遗忘的权利
- DOI:10.1145/3576915.3616585
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Cohen, Aloni;Smith, Adam;Swanberg, Marika;Vasudevan, Prashant Nalini
- 通讯作者:Vasudevan, Prashant Nalini
{{
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 }}
Adam Smith其他文献
Adam Smith's moral and political philosophy
亚当·斯密的道德和政治哲学
- DOI:
10.2307/2019387 - 发表时间:
2007 - 期刊:
- 影响因子:0
- 作者:
Adam Smith;H. Schneider - 通讯作者:
H. Schneider
Noise controls for roof bolting machines
屋顶锚杆机的噪声控制
- DOI:
- 发表时间:
2009 - 期刊:
- 影响因子:0
- 作者:
P. Kovalchik;Adam Smith;R. Metetic;J. Peterson - 通讯作者:
J. Peterson
Adam Smith's Social Deception, Individual Deception and Institutions
亚当·斯密的社会欺骗、个人欺骗和制度
- DOI:
- 发表时间:
2003 - 期刊:
- 影响因子:0
- 作者:
C. Gerschlager;Adam Smith - 通讯作者:
Adam Smith
The Invisible Hook The Hidden Economics of Pirates
看不见的钩子 海盗的隐藏经济
- DOI:
- 发表时间:
2009 - 期刊:
- 影响因子:0
- 作者:
Adam Smith;Meet Captain Hook - 通讯作者:
Meet Captain Hook
Adam Smith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('Adam Smith', 18)}}的其他基金
Towards a practical quantum advantage: Confronting the quantum many-body problem using quantum computers
迈向实用的量子优势:使用量子计算机应对量子多体问题
- 批准号:
EP/Y036069/1 - 财政年份:2024
- 资助金额:
$ 45万 - 项目类别:
Research Grant
Travel: Student Travel Grant for 2022 Boston Differential Privacy Summer School
旅行:2022 年波士顿差异隐私暑期学校学生旅行补助金
- 批准号:
2227905 - 财政年份:2022
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
CAREER: Lipid Regulation of Receptor Tyrosine Kinases
职业:受体酪氨酸激酶的脂质调节
- 批准号:
2308307 - 财政年份:2022
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
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
- 批准号:
2120667 - 财政年份:2021
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
Doctoral Dissertation Improvement Award:Examination of Multiple Chronologies
博士论文改进奖:多年表审查
- 批准号:
2106251 - 财政年份:2021
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
Collaborative Research: ERASE-PFAS: Remediation of Per- and Polyfluoroalkyl Substances in Wastewater using Anaerobic Membrane Bioreactors
合作研究:ERASE-PFAS:使用厌氧膜生物反应器修复废水中的全氟烷基和多氟烷基物质
- 批准号:
2112651 - 财政年份:2021
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
AF: Medium: Collaborative Research: Foundations of Adaptive Data Analysis
AF:媒介:协作研究:自适应数据分析的基础
- 批准号:
1763786 - 财政年份:2018
- 资助金额:
$ 45万 - 项目类别:
Continuing Grant
Collaborative Research: ABI Innovation: Quantifying biogeographic history: a novel model -based approach to integrating data from genes, fossils, specimens, and environments
合作研究:ABI 创新:量化生物地理历史:一种基于模型的新颖方法来整合来自基因、化石、标本和环境的数据
- 批准号:
1759708 - 财政年份:2018
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
CAREER: Lipid Regulation of Receptor Tyrosine Kinases
职业:受体酪氨酸激酶的脂质调节
- 批准号:
1753060 - 财政年份:2018
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
Collaborative Research: Social brains and solitary bees: A phylogenetic test of the effect of social behavior on brain evolution across multiple gains and losses of sociality
合作研究:社交大脑和独居蜜蜂:社会行为对大脑进化影响的系统发育测试,涉及社交性的多种得失
- 批准号:
1755375 - 财政年份:2018
- 资助金额:
$ 45万 - 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: 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:
$ 45万 - 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:
2330940 - 财政年份:2024
- 资助金额:
$ 45万 - 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:
$ 45万 - 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:
$ 45万 - 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:
$ 45万 - 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:
$ 45万 - 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:
$ 45万 - 项目类别:
Standard Grant
Collaborative Research: SaTC: EDU: Adversarial Malware Analysis - An Artificial Intelligence Driven Hands-On Curriculum for Next Generation Cyber Security Workforce
协作研究:SaTC:EDU:对抗性恶意软件分析 - 下一代网络安全劳动力的人工智能驱动实践课程
- 批准号:
2230609 - 财政年份:2023
- 资助金额:
$ 45万 - 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:
$ 45万 - 项目类别:
Standard Grant
Collaborative Research: SaTC: CORE: Medium: Understanding the Impact of Privacy Interventions on the Online Publishing Ecosystem
协作研究:SaTC:核心:媒介:了解隐私干预对在线出版生态系统的影响
- 批准号:
2237329 - 财政年份:2023
- 资助金额:
$ 45万 - 项目类别:
Standard Grant