/Systems And Methods For Secure Linear Operations In Machine Learning Via Homomorphic Aggregates
Abstract

A system obtains a weight matrix associated with a linear operation, the weight matrix comprising a first non-zero value and a second non-zero value that is a negative value. The system decomposes the weight matrix into a first binary matrix indicating positions of the first non-zero value and a second binary matrix indicating positions of the second non-zero value. The system encrypts vector elements of an input vector using an encryption scheme to obtain an encrypted input vector. For each row of the first and second binary matrices, the system homomorphically processes selected encrypted elements of the encrypted input vector to generate at least two intermediate encrypted aggregates corresponding to respective contribution signs. The system generates an output element for each row based on a combination of the intermediate encrypted aggregates.

Full Text

What is claimed is:

A system obtains a weight matrix associated with a linear operation, the weight matrix comprising a first non-zero value and a second non-zero value that is a negative value. The system decomposes the weight matrix into a first binary matrix indicating positions of the first non-zero value and a second binary matrix indicating positions of the second non-zero value. The system encrypts vector elements of an input vector using an encryption scheme to obtain an encrypted input vector. For each row of the first and second binary matrices, the system homomorphically processes selected encrypted elements of the encrypted input vector to generate at least two intermediate encrypted aggregates corresponding to respective contribution signs. The system generates an output element for each row based on a combination of the intermediate encrypted aggregates.
Timeline
Filed
03/25/2026
Published
07/23/2026
Granted
Not Available
IPC Codes(9)
H04L 9/00:Arrangements for secret or secure communications; Network security protocols
G06F 17/16:Matrix or vector computation
G06F 21/60:Protecting data