← NSFGrants
HomeNsf Awards

PDaSP: Track 3: Rigorous and Performant Differentially Private Machine Learning via OpenDP — NSF Award to Harvard University (MA,

Artificial intelligence systems are increasingly trained using datasets containing private information about individuals in critical areas such as government services, healthcare, and education. However, these AI systems have a demonstrated risk of accidentally revealing sensitive personal information about the people

Award titlePDaSP: Track 3: Rigorous and Performant Differentially Private Machine Learning via OpenDP
Award ID2453009
AwardeeHarvard University
CityCAMBRIDGE
StateMA
Amount obligated$800,000
Principal investigatorSalil Vadhan
ProgramNSF-Intel Semiconductr Partnrs, Privacy Preserving Data Sharin
Start date10/01/2025
AbstractArtificial intelligence systems are increasingly trained using datasets containing private information about individuals in critical areas such as government services, healthcare, and education. However, these AI systems have a demonstrated risk of accidentally revealing sensitive personal information about the people whose data was used during training, creating serious privacy and security concerns. This problem threatens public trust in AI technologies and creates barriers to beneficial uses
SourceNSF Awards

🔍 Search all NSF awards →