Skip to main content
U.S. flag

An official website of the United States government

Dot gov

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Https

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

2020 Differential Privacy Temporal Map Challenge

Graphic with text that reads: Differential Privacy Temporal Map Challenge

Visit the Challenge Website.

Visit Challenge.gov for the Official Rules

Open for submissions October 1, 2020 - May 17, 2021


Winners

Submission Contest Place/Prize Amount
MGD: A Utility Metric for Private Data Publication Metrics Contest 1st  $5,000
Practical DP Metric Metrics Contest 2nd $3,000
Confusion Matrix Metric Metrics Contest 2nd $3,000
Bounding Utility Loss via Classifiers Metrics Contest 3rd $2,000
Confusion Matrix Metric Metrics Contest People's Choice Award $1,000
Team Contest Place/Prize Amount

Minutemen

Sprint 1 1st $10,000
DPSyn_S Sprint 1 2nd $7,000
SyrDP Sprint 1 3rd $5,000
N - CRiPT Sprint 1 4th $2,000
Duke DP Team Sprint 1 5th $1,000
Duke DP Team Sprint 1 Progressive Prize $1,000
3401 Walnut Sprint 1 Progressive Prize $1,000
Minutemen Sprint 1  Progressive Prize $1,000
DPSyn_S Sprint 1 Progressive Prize $1,000

Apply differential privacy over space and time

Large data sets containing personally identifiable information (PII) are exceptionally valuable resources for research and policy analysis in a host of fields supporting America's First Responders such as emergency planning and epidemiology.

Temporal map data—information that is geographically situated and may change over time—is of particular interest to the public safety community in applications such as optimizing response time and personnel placement, natural disaster response, epidemic tracking, demographic data and civic planning. Yet, the ability to track a person's location over a period of time presents particularly serious privacy concerns.  

The Differential Privacy Temporal Map Challenge will invite solvers to develop algorithms and metrics that preserve data utility while guaranteeing individual privacy is protected. 

Participants will compete in a series of coding sprints using differential privacy methods on temporal map data. These data sets may contain the records of hundreds or thousands of individuals, each contributing to a sequence of events. The goal is to create a privacy-preserving dashboard map that shows changes across different map segments over time. 

The best solutions will be publicly recognized and up to $276,000 in cash prizes may be awarded to top-performing teams.

Elements of the challenge

The NIST PSCR Differential Privacy Temporal Map Challenge follows on the success of the 2018 Differential Privacy Synthetic Data Challenge, extending the reach and utility of differential privacy algorithms.

  • Temporal map data: The challenge will feature public safety data sets with geographic and temporal elements. Solutions will seek to satisfy differential privacy while preserving characteristics of original data sets as much as possible, including sequential data and geographic characteristics.
  • Utility metrics: Participants may submit white papers on new and innovative ways of measuring the accuracy of data sets produced by differential privacy algorithms.
  • De-identification algorithms: Participants build and submit algorithms to preserve data accuracy while guaranteeing privacy on temporal map data sets.
  • Open source development: Beyond expanding the types of data that can be made differentially private, this challenge seeks to advance and disseminate the resulting software. 

 View the Challenge Flyer!

Timeline for Metric Paper Contest 

Preregistration August 24, 2020
Open to submissions October 1, 2020 - January 5, 2021
NIST PSCR Compliance check (for public voting)  January 5-6, 2021
Public voting January 8-21, 2021
Judging and Evaluation January 5, 2021 - February 2, 2021
Winners Announced February 4, 2021

Timeline for Algorithm Contest

Preregistration August 24, 2020
Sprint #1 - Participation October 1, 2020 - November 15, 2020
Sprint #1 - Evaluation November 15, 2020 - December 11, 2020
Sprint #1 - Winners announced January 5, 2021
Sprint #2 - Participation January 6, 2021 - February 22, 2021
Sprint #2 - Evaluation February 22, 2021 - March 22, 2021
Sprint #2 - Winners announced March 23, 2021
Sprint #3 - Participation March 29, 2021 - May 17, 2021
Sprint #3 - Evaluation May 17, 2021 - June 15, 2021
Sprint #3 - Winners announced June 16, 2021

Timeline for Open Source and Development Contest

Open Source Deposit - Submissions due July 5, 2021
Development Plan - Submissions due July 5, 2021
Development Plan - Evaluation July 5-9, 2021
Development Plan - Winners announced July 14, 2021
Development Execution - Submission due October 9, 2021
Development Execution - Evaluation October 9-23, 2021
Development Execution - Winners announced October 27, 2021

*NOTE: NIST reserves the right to revise the dates at any time

Resources

Looking for great resources to get started? Here are a few ways to learn more about the math behind differential privacy.

Email: psprizes@nist.gov

Created September 1, 2020, Updated February 16, 2021