This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) provides $189,898 to the Regents of the University of Minnesota to accelerate the development of efficient, scalable, and practical privacy-preserving machine learning (ML) services. The project aims to advance trustworthy artificial intelligence, a key national strategic priority, by tackling critical technical bottlenecks in private ML. The research thrusts include optimizing information representation and model sparsity in the encryption domain, overcoming high overhead in multi-party computation-based solutions, and designing crypto-friendly neural architectures. This award reflects NSF's mission to support fundamental research that deepens understanding of the interactions among cryptography, machine learning, and hardware acceleration. The project runs from October 1, 2024 to August 31, 2027 and does not involve any sub-awards.
Generated 2/25/25, 3:36 AM