U.S. PETs Prize Challenge: Phase 2 (Pandemic Forecasting) Hosted By NIST and NSF
PETs Prize Challenge: Advancing Privacy-Preserving Federated Learning
This is the second in a series of challenge phases with a total prize pool of $800,000! Each phase in the PETs Prize Challenge invites participants to test and apply their innovations in privacy-preserving federated learning. Phase 2 is for Blue Teams to implement and submit working code for their solutions.
You are on the Phase 2 home page for the Pandemic Forecasting Data Track. You can find the Financial Crime Data Track here.
Privacy-enhancing technologies (PETs) have the potential to unlock more trustworthy innovation in data analysis and machine learning. Federated learning is one such technology that enables organizations to analyze sensitive data while providing improved privacy protections. These technologies could advance innovation and collaboration in new fields and help harness the power of data to tackle some of our most pressing societal challenges.
That’s why the U.S. and U.K. governments are partnering to deliver a set of prize challenges to unleash the potential of these democracy-affirming technologies to make a positive impact. In particular, this challenge will tackle two critical problems via separate data tracks: Data Track A will help with the identification of financial crime, while Data Track B will bolster pandemic responses.
By entering the prize challenges, innovators will have the opportunity to compete for cash prizes and engage with regulators and government agencies. Announced at the Summit for Democracy in December 2021, the prize challenges are a product of a collaboration between multiple government departments and agencies on both sides of the Atlantic. Winning solutions will have the opportunity to be profiled at the second Summit for Democracy, to be convened by President Joe Biden, in early 2023.
The goal of this prize challenge is to mature federated learning approaches and build trust in their adoption. The challenge organizers hope to accelerate the development of efficient privacy-preserving federated learning solutions that leverage a combination of input and output privacy techniques to:
- Drive innovation in the technological development and application of novel privacy-enhancing technologies
- Deliver strong privacy guarantees against a set of common threats and privacy attacks
- Generate effective models to accomplish a set of predictive or analytical tasks that support the use cases
The Solution Development Phase will have two data use case tracks matching those previously from the Concept Paper Phase—Track A: Financial Crime Prevention and Track B: Pandemic Response and Forecasting. Teams can elect to participate in either or both tracks, with solutions that apply to one track individually or with a generalized solution. Each solution must correspond to a concept paper that met the requirements from the Concept Paper Phase.
Each data use case track has a prize category for top solutions. All solutions that apply to Track A or Track B are eligible for a prize within that respective track. Teams who submit solutions for Track A and Track B are eligible to win a prize from each track.
Additionally, participants can enter a third Generalized Solutions category of prizes for the best solutions that are shown to be generalized and applied to both use cases with minor adaptations. Teams submitting generalized solutions are eligible for Generalized Solution prizes in addition to being eligible for prizes from both Track A and Track B.
Data Track A – Financial crime prevention – The United Nations estimates that up to $2 trillion of cross-border money laundering takes place each year, financing organized crime and undermining economic prosperity. Financial institutions such as banks and credit agencies, along with organizations that process transactions between institutions, such as the SWIFT global financial messaging provider, must protect personal and financial data, while also trying to report and deter illicit financial activities. Using synthetic datasets provided by SWIFT, you will design and later develop innovative privacy-preserving federated learning solutions that facilitate cross-institution and cross-border anomaly detection to combat financial crime. This use case features both vertical and horizontal data partitioning. Check out the Financial Crime overview page for more information.
Data Track B – Pandemic response and forecasting – As we continue to deal with COVID-19, it has become apparent that better ways to harness the power of data through analytics are critical for preparing for and responding to public health crises. Federated learning approaches could allow for responsible use of sensitive data to develop cross-organization and cross-border data analysis that would result in more robust forecasting and pandemic response capabilities. Using synthetic population datasets, you will design and later develop privacy-preserving federated learning solutions that can predict an individual’s risk for infection. This use case features horizontal data partitioning. Check out the Pandemic Forecasting overview page for more information.
Generalizable Solutions – Cross-organization, cross-border use cases are certainly not limited to the financial or public health domains. Developing out-of-the-box generalized models that can be adapted for use with specific data or problem sets has great potential to advance the adoption and widespread use of privacy-preserving federated learning for public- and private-sector organizations in multiple sectors. To demonstrate generalizability, you may develop a solution using both the Track A and Track B datasets to be eligible for additional awards dedicated to generalizable solutions.
More information on how to get started can be found in the Problem Description.
Phase 2 is open to Blue Team Participants who won invitations because their Concept Papers met the minimum criteria described in the challenge rules. No further registration will be required for the invitees to advance to Phase 2; however, invited Blue Team Participants should make necessary updates to their registration via their DrivenData account to reflect any changes in team composition or contact information. For more details, please refer to the official rules.
Phase 2 Timeline and Prizes
Phase 2 Key Dates
|Launch||October 5, 2022|
|Deadline to Open Pull Requests for Runtime Environment||January 4, 2023 at 11:59:59 PM UTC|
|Submissions Due||January 24, 2023 at 11:59:59 PM UTC|
|Announcement of Finalists to be Tested in Phase 3 Red Teaming||February 13, 2023|
|Winners Announced||March 17, 2023|
Phase 2 Prizes
Open to Blue Team participants.
Data Track A: Financial Crime Prevention
Data Track B: Pandemic Response and Forecasting
Put your papers into action! Registered teams from Phase 1 will develop working prototypes and submit them to a remote execution environment for federated training and evaluation. These solutions are expected to be functional, i.e., capable of training a model and predicting against the evaluation data set with measurement of relevant performance and accuracy metrics. Solutions will be evaluated by a panel of judges across a set of weighted criteria. The top solutions, ranked by points awarded, will have their final rankings determined by incorporating red team evaluation from the red teams from Phase 3.
Teams can qualify for one or multiple of Data Track A: Financial Crime Prevention, Data Track B: Pandemic Response and Forecasting, and Generalized Solutions prize categories depending on how their solutions address the two privacy-preserving federated learning tasks in the challenge.
A separate Special Recognition prize pool is set aside to award up to five solutions that do not win prizes from the three main prize categories but demonstrate excellence in specific areas of privacy innovation: novelty, advancement in a specific privacy technology, usability, and efficiency.
Full Challenge Timeline and Prizes
There are three main phases in the challenge with two types of participants based on a red team/blue team approach. Blue Teams develop privacy-preserving solutions, while Red Teams act as adversaries to test those solutions.
- Phase 1: Concept Development (Jul–Sept 2022): Blue Teams propose privacy-preserving federated learning solution concepts.
- Phase 2: Solution Development (Oct 2022–Jan 2023): Blue Teams develop working prototypes of their solutions.
- Phase 3: Red Teaming (Nov 2022–Feb 2023): Red Teams prepare and test privacy attacks on top blue team solutions from Phase 2.
Additional Phase Details and Prizes
Phase 1: Concept Paper
July 20–September 19, 2022
Participants will produce an abstract and technical concept paper laying out their proposed solution. Concept papers will be evaluated by a panel of judges across a set of weighted criteria. Participants will be eligible to win prizes awarded to the top technical papers, ranked by points awarded. Participants must complete a paper in Phase 1 in order to be eligible to compete in Phase 2.
Open to Blue Team participants.
Phase 3: Red Teaming
November 10, 2022–February 28, 2023
Privacy researchers are invited to form red teams to put the privacy claims of Phase 2's blue team finalists to the test. The red teams will prepare and test privacy attacks on the Phase 2 finalist solutions, which will be incorporated into the final Phase 2 rankings. Top red teams will be evaluated for success and rigor and will be awarded prizes for their performance during this phase.
Open to Red Team participants.
Submissions due April 7, 2023
Up to 5 of the final blue team winners from Phase 2 will be invited to release their solutions as open-source software. Each verified participating blue team will be awarded an Open Source prize of $10,000.
Open to top Blue Team winners from Phase 2.
How to compete (Phase 2)
- Only blue teams who participated in Phase 1 and met minimum requirements are eligible to participate in Phase 2. Eligible teams are automatically registered. If you need to make changes to your team, please contact email@example.com.
- Get familiar with the problem through the problem description and code submission format pages.
- Develop and submit your centralized solution. Check out the centralized code submission format page for more details.
- Develop and submit your federated solution. Check out the federated code submission format page for more details.