US 12,132,669 B1
Resource allocation in secure computation and communication
Sagar Sharma, Culver City, CA (US); and Qiang Yan, Beijing (CN)
Assigned to LEMON INC., Grand Cayman (KY)
Filed by Lemon Inc., Grand Cayman (KY)
Filed on May 15, 2023, as Appl. No. 18/317,483.
Int. Cl. G06F 15/16 (2006.01); H04L 41/16 (2022.01); H04L 47/80 (2022.01); H04L 47/83 (2022.01)
CPC H04L 47/83 (2022.05) [H04L 41/16 (2013.01); H04L 47/808 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for allocating a resource of a differentially private system in secure computation and communication, the method comprising:
providing a usage log including operation information of the differentially private system, the differentially private system having a privacy budget parameter indicative of a strength of a data privacy protection and a probability parameter indicative of a data privacy loss;
aggregating attributes from the usage log of the differentially private system for a predetermined period of time, the privacy budget parameter and the probability parameter forming at least a part of the attributes;
generating a windowed moving aggregation based on the aggregated attributes;
training a machine learning model based on the aggregated attributes and the windowed moving aggregation to minimize an overall error of an attribute of the attributes;
predicting a distribution of the resource using the trained machine learning model; and
allocating the resource based on the predicted distribution.