NSF/FHWA PDaSP Track 2

A Holistic Privacy Preserving Collaborative Data Sharing System for Intelligent Transportation

This multi-institution NSF-funded project develops privacy-preserving data sharing, analytics, and cyberinfrastructure for next-generation Intelligent Transportation Systems (ITS). The effort integrates expertise across privacy, transportation systems, cyber-physical systems, and education to enable responsible, scalable, and deployable use of sensitive transportation data.

Project overview Research areas NSF Award 2452747
PDaSP banner

Privacy-Preserving Data Sharing in Practice (PDaSP)

Aligned research across four institutions to deliver deployable privacy-preserving ITS data infrastructure.

Project overview

Modern ITS generate large-scale, heterogeneous, and highly sensitive data from vehicles, infrastructure, and V2X communications. While these data are critical for improving safety, mobility, and sustainability, privacy concerns and regulatory constraints significantly limit their sharing and use.

This project addresses these challenges by developing holistic, privacy-preserving methods and systems that balance data utility, strong privacy guarantees, system efficiency, and policy compliance.

Project snapshot

  • Scope: Multi-institution ITS privacy collaboration
  • Focus: Privacy-preserving data sharing and analytics
  • Systems: Scalable, deployable cyberinfrastructure
  • Impact: Responsible use of sensitive transportation data

Holistic Privacy Protection for Real-world ITS Deployments

Intelligent transportation systems generate enormous volumes of data—from vehicle trajectories and roadway conditions to video feeds captured during everyday travel. These datasets are indispensable for improving safety, reducing congestion, and enabling next-generation mobility technologies. At the same time, they contain sensitive personal information that restricts how agencies, companies, and researchers can share and use them.

This project develops an end-to-end privacy-preserving platform that enables secure, policy-compliant sharing of diverse ITS data across organizational boundaries. It adapts and scales modern privacy techniques for both centralized and distributed environments, ensuring that data remains useful while meeting stringent protection requirements. By doing so, the work strengthens transportation safety, supports the competitiveness of autonomous and connected vehicle technologies, and enhances infrastructure resilience through data-driven decision making.

The platform integrates a web-based tool that recommends appropriate privacy methods, formal auditing and compliance capabilities, secure cyberinfrastructure built with public and private partners, and extensive evaluation using real-world transportation datasets.

Targeted data types

  • Vehicle and road user data (speed, travel times, trajectories)
  • Infrastructure data (traffic flow, control states)
  • Videos captured during actual trips
  • Naturalistic driving data from in-vehicle sensors and mobile devices

Platform features

  • Privacy-preserving techniques for centralized and distributed sharing
  • Web-based recommendation system for technique selection
  • Audit and compliance tools based on formal guarantees
  • Secure cyberinfrastructure with public/private partners
  • Evaluation on real-world transportation datasets

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.

Research areas

Five coordinated thrusts guide the research agenda.

Privacy-preserving data sharing

Differential privacy, secure computation, and federated learning techniques.

Transportation and ITS applications

Traffic modeling, mobility behavior, and connected vehicle analytics.

Systems and cyberinfrastructure

Scalable platforms, real-time processing, and trusted execution.

Policy, auditability, and trust

Privacy auditing, regulatory compliance, and interpretability.

Deployment and evaluation

Real-world datasets, testbeds, and performance validation.

Team

The project team spans four institutions and includes experts in privacy and security, transportation and intelligent transportation systems, systems and cyber-physical systems, and education and workforce development.

Institutional leads

  • University of Connecticut (Lead): Yuan Hong (PI), Song Han (Co-PI)
  • University of Washington: Xuegang Ban (PI), Angela Kitali (Co-PI)
  • Illinois Institute of Technology: Binghui Wang (PI)
  • Iowa State University: Meisam Mohammady (PI)

Expertise areas

  • Privacy and Security
  • Transportation and Intelligent Transportation Systems
  • Systems and Cyber-Physical Systems
  • Education and Workforce Development

NSF awards

  1. UNIVERSITY OF CONNECTICUT (2452747)
  2. UNIVERSITY OF WASHINGTON (2452750)
  3. ILLINOIS INSTITUTE OF TECHNOLOGY (2452748)
  4. IOWA STATE UNIVERSITY OF SCIENCE AND TECHNOLOGY (2452749)

Collaborations and partners

The project collaborates with federal and public agencies including FHWA and USDOT, as well as state and city transportation agencies, university transportation centers, and industry and data partners. Additional partnerships are actively being developed.

Delivered products

Privacy-preserving software platforms

Foundational infrastructure for secure ITS data exchange.

Algorithms and methods

Secure analytics tailored to transportation applications.

Benchmark datasets

Evaluation frameworks and real-world performance baselines.

Privacy auditing tools

Compliance tooling and transparency metrics.

Publications

Selected publications produced as a result of this research.

PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization

Yang, Qin; Stout, Nicholas; Mohammady, Meisam; Wang, Han; Samreen, Ayesha; Quinn, Christopher J; Yan, Yan; Kundu, Ashish; Hong, Yuan (2025). DOI: 10.1145/3719027.3765151

Future research outcomes

The project will produce new privacy technologies for ITS, deployable systems for agencies, policy-relevant insights on data sharing and privacy, and a trained workforce prepared to advance trustworthy transportation systems.

What success looks like

  • Deployable systems for transportation agencies
  • Policy-relevant insights on data sharing
  • Trustworthy privacy technologies for ITS
  • Workforce prepared for privacy-first mobility

Education and outreach

The project supports graduate and undergraduate research training, integrates results into university curricula, engages minority-serving institutions, and conducts outreach to K–12 students and the broader public.

Education commitments

  • Graduate and undergraduate research training
  • Curriculum integration at partner universities
  • Engagement with minority-serving institutions
  • K–12 and public outreach programs

Funding and acknowledgment

This work is supported by multiple National Science Foundation awards across four institutions. Any opinions, findings, and conclusions expressed are those of the authors and do not necessarily reflect the views of the NSF.

Sponsors