SaTC: CORE: Small: A Novel Mechanism for Effective and Accountable Communication of Differential Privacy through Multi-Stakeholder Research
- Institution
- University of Vermont & State Agricultural College, VT
- Principal investigator
- Yuanyuan Feng
- Funding
- $600K
- Duration
- 2024–2027
Moonbase score
Still being scored
Abstract
Differential privacy is a state-of-the-art computing technique to protect individual data privacy in a dataset while allowing meaningful statistical analyses on the dataset. Currently, many barriers inhibit the implementation of differential privacy in real-world computing systems, one of which is the difficulty of communicating a specific system's actual privacy protection afforded by its differential privacy implementation. This project designs a standardized differential privacy certificate (DP certificate) to effectively communicate the privacy protection afforded by differential privacy to audiences with varying technical backgrounds, creates technical methods to ensure the contents of the DP certificate are accountable, and develops a software toolkit to help generate the DP certificate for a given system. The project's novelty is to create an effective and accountable way to communicate the actual privacy protection of differential privacy. The project's broader significance includes establishing a communication standard and facilitating the broader adoption of differential privacy. This project involves multi-area computing research. It includes a series of human subject research with multiple differential privacy stakeholder groups (e.g., differential privacy adopters, the general public, and differential privacy and standardization experts) to design a standardized DP certificate that can be understood by audiences with varying technical backgrounds, as well as formal methods research to create an accountability framework and relevant verification tools to verify key parameters on a DP certificate against the actual system. This project also develops a proof-of-concept software toolkit that helps differential privacy adopters create accountable DP certificates for their systems so that they can publicize their systems' privacy protection to the general public. The project outcomes establish a novel mechanism for effective and accountable communication of differential privacy, as well as widen the adoption and acceptance of differential privacy in real-world computing systems. This project's broader impacts include creating a differential privacy communication standard through the DP certificate, increasing public trust in differential privacy through the formal verification of privacy guarantee, and cultivating stakeholder appreciation for differential privacy through collaborative dissemination activities. 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 team
- Yuanyuan FengPI
- Joseph Near
LOADING MOONBASE SCORE
Questions for University of Vermont & State Agricultural College
Answered by the team behind this research.
No questions yet. Sign in to ask the first one
Related grants
Same researchers, same institution, same topic, scored first.
- NSF · University of Vermont & State Agricultural College43
CAREER: Distributed Differential Privacy via Secure Multiparty Computation
Joseph Near · $549K · 2023–2028
- NSF · University of Vermont & State Agricultural CollegeNot yet scored
Collaborative Research: III: Toward Robust and Private Cross-view Geo-localization
Safwan R Wshah · $678K · 2026–2030
- NSF · University of Vermont & State Agricultural CollegeNot yet scored
CRII: SaTC: A Contextual Integrity Approach for Privacy Reasoning Regarding Performance Tracking Technologies in US College Athletics
Yuanyuan Feng · $175K · 2024–2027