RAPID: Collaborative: REACT: Real-time Contact Tracing and Risk Monitoring via Privacy-enhanced Mobile Tracking

接触者追踪对于控制流行病暴发至关重要，例如快速增长的COVID-19大流行。个人的实时位置跟踪可用于显著加快和扩大接触追踪。然而，这种使用也加剧了对个人隐私和数据滥用的担忧。COVID-19大流行的紧迫性需要在隐私保护与公共卫生利益之间取得谨慎的平衡。该项目旨在开发技术和移动应用程序REACT，通过对用户位置和症状的隐私增强跟踪，实现实时接触追踪和风险监控。为了增强隐私，用户可以控制和细化收集和使用其信息的频率和粒度。应急反应将使：1)对确诊病例接触过的个人和地点进行接触者追踪，以便进行隔离和消毒，以控制进一步传播；2)根据他们访问的地点和与其他人接触的情况对个人进行风险监测，以便向他们通报情况并发出警报；3)开展社区风险监测，发现社区传播的早期信号，为应对更大规模感染做好准备。该项目将开发和研究：1)高效和可扩展的数据结构和算法，用于提供大量用户和多分辨率位置跟踪查询；2)基于学习的用户风险实时建模方法；3)采用社交网络传感器方法监测社区风险；4)采用多阶段隐私保护方法，用户可以上传一般化的位置，以便在被告知可能与确诊病例接触时接收警报和更精确的位置，以便进行细化和确认。将研究更严格的隐私增强功能，包括基于地理不可分辨性及其变体的位置扰动，以及在加密位置上进行接触追踪的可搜索加密。除此之外，项目还包括一系列的传播教育活动：1)发布一个使用开源系统组件的移动应用；2)研究隐私保护机制，共享收集的数据用于研究；3)将研究与课堂结合，组织系列讲座和辅导课，推动跨学科研究领域的发展。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。

Contact tracing is critical for controlling epidemic disease outbreaks such as the fast-growing COVID-19 pandemic. Real-time location traces of individuals can be used to significantly speed up and scale up contact tracing. However, such use also heightens concerns on individual privacy and data abuse. Urgency of the COVID-19 pandemic requires a careful balance of privacy protection with public health benefits. This project aims to develop techniques and a mobile application, REACT, for REAal-time Contact Tracing and risk monitoring via privacy-enhanced tracking of users' locations and symptoms. To enhance privacy, users can control and refine the frequency and granularity with which their information will be collected and used. REACT will enable: 1) contact tracing of individuals and locations that a confirmed case has contact with for quarantine and decontamination to control further spread, 2) individual risk monitoring based on the locations they visit and their contact with others so they can be informed and alerted; and 3) community risk monitoring and detection of early signals of community spread to prepare for larger-scale infections. The project will develop and study: 1) efficient and scalable data structures and algorithms for contact tracing queries given a large number of users and multi-resolution location traces; 2) a learning-based approach for modeling users’ risks in real time; 3) a social network sensors approach for monitoring the community risk, and 4) a multi-stage privacy approach where users can upload generalized locations to receive alerts and more precise locations when they are notified as possible contacts with confirmed cases for refinement and confirmation. More rigorous privacy enhancements will be studied including location perturbation based on geo-indistinguishability and its variants and searchable encryption for contact tracing on encrypted locations. In addition, the project includes a set of dissemination and education activities: 1) releasing a mobile app with open-source system components; 2) investigating privacy-preserving mechanisms to share the collected data for research studies; and 3) integrating the research in classes and organizing seminar series and tutorials to promote the interdisciplinary research area.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.