The National Science Foundation awarded a $174,855 Project Grant to Michigan Technological University under the Computer and Information Science and Engineering program (CFDA 47.070). The grant supports development of techniques to enable secure machine learning queries over encrypted databases in cloud computing. Specifically, the university will develop an index-aided approach employing encryption of individual data items and generation of secure index items to simultaneously achieve strong data privacy and machine learning capability. This addresses the conflict between data security and utility. The university will also develop artificial intelligence-driven encryption and masking techniques outperforming differential privacy and homomorphic encryption methods regarding privacy and runtime performance. The work furthers the program's goals of supporting investigator-initiated computing and information science and engineering research.
Generated 1/7/24, 2:22 AM