CAREER: Privacy-aware Predictive Modeling of Dynamic Human Events

职业：动态人类事件的隐私感知预测建模

基本信息

批准号：
1943486
负责人：
Mingxuan Sun
金额：
$ 42.28万
依托单位：
Louisiana State University
依托单位国家：
美国
项目类别：
Continuing Grant
财政年份：
2020
资助国家：
美国
起止时间：
2020-06-01 至 2025-05-31
项目状态：
未结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1943486&HistoricalAwards=false
关键词：
CAREER Privacy aware Predictive Modeling

项目摘要

Machine learning that leverages individuals' event data can improve the prediction accuracy of future events, but introduces high risks to each individual's privacy. Nowadays, large volumes of human event data, such as online TV-viewing records, domain name server queries, and electronic records of hospital admissions, are becoming increasingly available in a wide variety of applications including network analysis and services and healthcare analytics. Predictive modeling of those collective event sequences is beneficial for promoting nationwide economic and safety development. For example, in network traffic diagnosis, the analysis of user activities can be used to predict and control dynamic traffic demand, which improves risk response efficiency. In health informatics, the analysis of patient admission events can detect and optimize treatment for individuals at risks, which enhances public health preparedness and healthcare outcomes. However, by optimizing for the unitary goal of accuracy, machine learning algorithms trained on historic event data may amplify privacy risks. Studies have demonstrated that it is possible to infer private attributes such as demographics and locations from human activities such as online browsing histories and location check-in events. This project is to develop a trusting-based machine learning framework that better protects human privacy while minimally impacting utility for predicting dynamic events. Research and education on interdisciplinary topics of machine learning and privacy are integrated in curriculum development, student research projects, and academic seminars.The project develops a series of novel models and algorithms to analyze dynamic human events in three synergistic research thrusts. (1) Besides time-stamped event sequences, additional marker information such as event types and tags can be utilized to better capture the dependencies between events. This project investigates novel point processes, multi-view learning, and deep learning methods for analyzing dynamic human events with event marker information. (2) To improve human understanding and trust of predictive modeling, the project develops interpretable algorithms to explain how their information is used in event prediction and what potential private information can be inferred based on their inputs. (3) Balancing between privacy and utility is of mutual benefit to both individuals and service providers. This project investigates a user-specific privacy-preserving approach for event prediction and addresses utility-privacy tradeoff by formulating it as a min-max optimization problem. These three research aims are complemented by a comprehensive evaluation in a number of application domains.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.

利用个人事件数据的机器学习可以提高未来事件的预测准确性，但会给每个人的隐私带来高风险。如今，大量人类活动数据（例如在线电视查看记录，域名服务器查询以及医院入院的电子记录）在包括网络分析和服务和医疗保健分析在内的各种应用程序中越来越多。这些集体事件序列的预测建模有益于促进全国经济和安全发展。例如，在网络流量诊断中，对用户活动的分析可用于预测和控制动态交通需求，从而提高风险响应效率。在健康信息学中，对患者入学事件的分析可以检测和优化有风险的人的治疗方法，从而增强公共卫生的准备和医疗保健结果。但是，通过优化准确性的统一目标，对历史事件数据进行培训的机器学习算法可能会扩大隐私风险。研究表明，可以从人类活动（例如在线浏览历史记录和位置登机活动）中推断出诸如人口统计和地点之类的私人属性。该项目是开发一个基于信任的机器学习框架，该框架可以更好地保护人类的隐私，同时最小化影响动态事件的实用程序。关于机器学习和隐私的跨学科主题的研究和教育纳入了课程开发，学生研究项目和学术研讨会。该项目开发了一系列新颖的模型和算法，以分析三个协同研究推力的动态人类事件。（1）除了时间stamp的事件序列外，还可以利用其他标记信息（例如事件类型和标签）来更好地捕获事件之间的依赖关系。该项目研究了新的点过程，多视图学习以及使用事件标记信息分析动态人类事件的深度学习方法。（2）为了提高人类对预测建模的理解和信任，该项目开发了可解释的算法，以解释如何在事件预测中使用其信息，以及可以根据其输入来推断哪些潜在的私人信息。（3）隐私与效用之间的平衡对个人和服务提供商都具有相互利益。该项目研究了事件预测的一种特定于用户的隐私方法，并通过将其作为最小值优化问题来解决公用事业私人关系的权衡。这三项研究的目标是在许多应用领域的全面评估中得到的补充。该奖项反映了NSF的法定任务，并且使用基金会的知识分子优点和更广泛的影响评估标准，被认为值得通过评估来获得支持。

项目成果

期刊论文数量（7）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

A Game-Theoretic Approach to Achieving Bilateral Privacy-Utility Tradeoff in Spectrum Sharing

DOI：
10.1109/globecom42002.2020.9322123
发表时间：
2020-12
期刊：
GLOBECOM 2020 - 2020 IEEE Global Communications Conference
影响因子：
0
作者：
Mengmeng Liu;Xiangwei Zhou;Mingxuan Sun
通讯作者：
Mengmeng Liu;Xiangwei Zhou;Mingxuan Sun

Bilateral Privacy-Utility Tradeoff in Spectrum Sharing Systems: A Game-Theoretic Approach

DOI：
10.1109/twc.2021.3065927
发表时间：
2021-08
期刊：
IEEE Transactions on Wireless Communications
影响因子：
10.4
作者：
Mengmeng Liu;Xiangwei Zhou;Mingxuan Sun
通讯作者：
Mengmeng Liu;Xiangwei Zhou;Mingxuan Sun

Sparse Transformer Hawkes Process for Long Event Sequences

长事件序列的稀疏变压器霍克斯过程

DOI：
发表时间：
2023
期刊：
Part V
影响因子：
0
作者：
Li, Zhuoqun;Sun, Mingxuan.
通讯作者：
Sun, Mingxuan.

Multivariate Hawkes Processes for Incomplete Biased Data

不完整偏差数据的多元霍克斯过程

DOI：
10.1109/bigdata52589.2021.9672043
发表时间：
2021
期刊：
IEEE International Conference on Big Data (Big Data
影响因子：
0
作者：
Zhou, Zihan;Sun, Mingxuan
通讯作者：
Sun, Mingxuan

List-wise Fairness Criterion for Point Processes

DOI：
10.1145/3394486.3403246
发表时间：
2020-07
期刊：
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
影响因子：
0
作者：
Jin Shang;Mingxuan Sun;N. Lam
通讯作者：
Jin Shang;Mingxuan Sun;N. Lam