menu

NASA Tournament Lab

 22,186

NIST Differential Privacy Synthetic Data Challenge

Propose a mechanism to enable the protection of personally identifiable information while maintaining a dataset's utility for analysis
stage:
Won
prize:
$150,000
Partners
more
Summary
Timeline
Updates10
Forum5
Teams166
Resources
FAQ
Summary

Overview

Are you a mathematician or data scientist interested in a new challenge? 

Then join this exciting data privacy competition with up to $150,000 in prizes, where participants will propose a mechanism to enable the protection of personally identifiable information while maintaining a dataset's utility for analysis using differentially private synthetic data generation tools.

Our increasingly digital world turns almost all our daily activities into data collection opportunities, from the more obvious entry into a webform to connected cars, cell phones, and wearables. Dramatic increases in computing power and innovation over the last decade along with both public and private organizations increasingly automating data collection make it possible to combine and utilize the data from all of these sources to complete valuable research and data analysis.

Due to the sensitive nature of information contained in these types of datasets, and the risk of individuals being identifiable even in anonymized data, these datasets can’t easily be made available to analysts and researchers.  Differentially private synthetic data generation solves this problem by producing new, artificial data that can serve as a practical replacement for the original sensitive data.  

The “Differential Privacy Synthetic Data Challenge” will entail a sequence of three marathon matches run on the Topcoder platform, asking contestants to design and implement their own synthetic data generation algorithms, mathematically prove their algorithm satisfies differential privacy, and then enter it to compete against others’ algorithms on empirical accuracy over real data, with the prospect of advancing research in the field of Differential Privacy.

Competitors may enter the contest at any point to participate between November 2018 and April 2019. Topcoder will be running three separate Marathon Matches and will bring the registrations from previous matches to the next matches.

 

Join, learn, and compete for $150,000 in prizes! 

 

If you’re not a differential privacy expert, and you’d like to learn, we’ll have tutorials to help you catch up and compete! 

Timeline
Updates10

Challenge Updates

Congratulations to the Winners in Match #3 of the Differential Privacy Synthetic Data Challenge

May 23, 2019, 2:31 p.m. PDT by Kyla Jeffrey

Congratulations to the Top 5 winners, and to all contestants in this Challenge!  The winners in Match #3 of the Differential Privacy Synthetic Data Challenge are:

 

1-st ($25,000) - 902,307 - rmckenna
2-nd ($15,000) - 870,097 - ninghui
3-rd ($10,000) - 823,512 - privbayes
4-th ($5,000) - 768,802 - gardn999
5-th ($3,000) - 541,494 - manisrivastava

 

And the progressive prize winners ($1,000 each), already announced earlier, are:

rmckenna
ninghui
privbayes
gardn999

 

For more details on the final review and scoring, head over to the Topcoder forum

Congratulations to all winners! You are helping NIST grow a diverse community that is maturing into robust solutions.  Your participation in this data challenge is incredibly important…highlighting different approaches that will become the basis for future growth and innovation while helping NIST establish a measurement-based approach to fostering data-driven R&D in this area.  Your involvement with PSCR ensures that this community considers the practical, applied use of differential privacy in public safety applications of the future.


Your Questions Answered

Feb. 1, 2019, 11:43 a.m. PST by Kyla Jeffrey

Did you attend the Match #2 Webinar? 

We answered your most pressing questions. If you missed it, you can watch the recording below and review the written Q&A here.

 

As a reminder, we are quickly approaching the Match 2 deadline on February 9, 2019 at 21:00 EST (New York). 

If you have any additional questions, please head over to the Topcoder Forums and we will do our best to answer them for you.


Q & A Webinar

Jan. 14, 2019, 5:47 p.m. PST by Kyla Jeffrey

We are hosting a Q & A webinar with the NIST and Topcoder on Tuesday, Jan 15 at 12:30 pm ET (New York). This will be a great opportunity to meet the sponsors, learn more, and ask your burning questions. 

 

Save Your Seat


Match 2 Launches Today!

Jan. 11, 2019, 6:30 p.m. PST by Kyla Jeffrey

We are thrilled to announce that the second marathon match officially opens for submission today!

The Differential Privacy Synthetic Data Challenge entails a sequence of three marathon matches run on the Topcoder platform, asking contestants to design and implement their own synthetic data generation algorithms, mathematically prove their algorithm satisfies differential privacy, and then enter it to compete against others’ algorithms on empirical accuracy over real data, with the prospect of advancing research in the field of Differential Privacy.

Anyone is welcome to participate in Match 2, regardless of whether or not you participated in Match 1. If you’re not a differential privacy expert, and you’d like to learn, we’ll have tutorials to help you catch up and compete!

For more information on this data challenge funded through Public Safety Communications Research (PSCR) at NIST, or any federal government challenge, go to Challenge.gov.

We are also hosting a webinar on Tuesday, Jan 15 at 12:30 pm ET (New York). This will be a great opportunity to meet the sponsors, learn more, and ask any questions. You can register for the webinar here.

 

Head over to the Topcoder Challenge Page to view the full details


Congratulations to the Winners in Match #1 of the Differential Privacy Synthetic Data Challenge

Jan. 1, 2019, 8:40 p.m. PST by Kyla Jeffrey

Congratulations to the Top 5 winners, and to all contestants in this Challenge!  The winners in Match #1 of the Differential Privacy Synthetic Data Challenge are:

1st ($10 000) - 781 953 - jonathanps
2nd ($7 000) - 736 780 - ninghui
3rd ($5 000) - 664 623 - rmckenna
4th ($2 000) - 93 955 - manisrivastava
5th ($1 000) - 82 414 - privbayes

For more details on the final review and scoring, head over to the Topcoder forum.

Differential privacy is an emerging research area. The work that each of you have done and will continue to do is critical to developing the knowledge and resources essential to expanding research in this area. You are helping NIST grow a diverse community that is maturing into robust solutions.  Your participation in this data challenge is incredibly important…highlighting different approaches that will become the basis for future growth and innovation while helping NIST establish a measurement-based approach to fostering data-driven R&D in this area.  Your involvement with PSCR ensures that this community considers the practical, applied use of differential privacy in public safety applications of the future.


Forum5
Teams166
Resources
FAQ