ANNOUNCEMENT

NOBEL PRIZE 2026

This year's laureates, their fields, and the discoveries that earned them the prize.Live nowSee the winners
Moonbase
← Back to Awards
NSFI-Corps

I-Corps: Artificial Intelligence Chain

Completed
Institution
Saint Mary's College of California, CA
Principal investigator
Navid Sabbaghi
Funding
$50K
Duration
2023–2024
Open portfolio

Moonbase score

Still being scored

Abstract

The broader impact/commercial potential of this I-Corps project is the development of a safety net for those individuals and organizations that would like confidentiality and protection when working with cryptocurrency. With this safety net, more cryptocurrency owners would feel comfortable entering the market, expanding the platform beyond the 1 billion members expected by 2023. Current blockchain participants have opened their identities and transactions for the world to see even though they risk the dangers that come with that transparency. Even participants that have not disclosed their wallet identities have found their true identities to have been compromised and have faced threats. When an owner conducts a large cryptocurrency transaction, the risk of damage due to exposure can be high whether it be for individuals or businesses. For those market segments, confidentiality - as a service enabled by this technology - would help lower the risk of exposure and thus reduce damage substantially. This I-Corps project is based on the development of a technology platform to enable confidentiality and transaction monitoring as a service for blockchain systems with the goal of reducing transaction costs and enhancing auditability. The core technology that undergirds the platform combines a machine learning algorithm with secure encryption techniques. This platform will satisfy regulatory requirements and provide safety as well as confidentiality for blockchain users and platforms. The approach uses machine learning, optimization, and encryption techniques to mask transactions and to provide confidentiality while also using machine learning algorithms to discern when suspicious activity is happening on the transaction graph. The privacy-preserving machine learning techniques have never been used in production in the context of blockchain. Intellectually, the algorithms enhance the understanding of the effectiveness of machine learning techniques on encrypted data. The technology will reduce financial crime while preserving confidentiality. 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.

LOADING MOONBASE SCORE

I-CorpsDirectorate for Technology, Innovation, and PartnershipsCOMPLEXITY & CRYPTOGRAPHYidentitiesconfidentialitysafety netencryptionblockchainlearning techniquestransactionsnet

Questions for Saint Mary's College of California

Answered by the team behind this research.

Same institution, same topic, scored first.