公开(公告)号：US11727037B2

公开(公告)日：2023-08-15

申请号：US17385105

申请日：2021-07-26

Applicant: Booz Allen Hamilton Inc.

Inventor： Fred Sun Lu ,  Edward Simon Paster Raff

IPC: G06F16/28 ,  G06N5/04

CPC classification number: G06F16/285 ,  G06N5/04

Abstract: A method and system for configuring a computer for data classification using ordinal regression includes: receiving and storing a data set having data with a plurality of data features that have an ordinal relationship; generating a plurality of ordinal classification bins based on the relationship of the data features, at least one ordinal classification bin having walls defined by at least two hyperplanes; generating an ordinal regression model of the data set illustrating the data of the data set arranged into the plurality of ordinal classification bins; and tuning the slopes of the walls of the at least one ordinal classification bin based on the relationships between the plurality of data features of the data arranged within the at least one ordinal classification bin such that the slopes of the two hyperplanes defining the walls of the at least one ordinal classification bin are not parallel.

公开(公告)号：US11948054B2

公开(公告)日：2024-04-02

申请号：US17083928

申请日：2020-10-29

Applicant: Booz Allen Hamilton Inc.

Inventor： Luke Edward Richards ,  Andre Tai Nguyen ,  Ryan Joseph Capps ,  Edward Simon Paster Raff

IPC: H04L9/40 ,  G06N20/00

CPC classification number: G06N20/00 ,  H04L63/1416 ,  H04L63/1466

Abstract: A system and method for transferring an adversarial attack involving generating a surrogate model having an architecture and a dataset that mirrors at least one aspect of a target model of a target module, wherein the surrogate model includes a plurality of classes. The method involves generating a masked version of the surrogate model having fewer classes than the surrogate model by randomly selecting at least one class of the plurality of classes for removal. The method involves attacking the masked surrogate model to create a perturbed sample. The method involves generalizing the perturbed sample for use with the target module. The method involves transferring the perturbed sample to the target module to alter an operating parameter of the target model.

公开(公告)号：US20240256963A1

公开(公告)日：2024-08-01

申请号：US18423774

申请日：2024-01-26

Applicant: Booz Allen Hamilton Inc.

Inventor： Edward Simon Paster Raff ,  Amol Ashish Khanna ,  Fred Sun Lu

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Exemplary systems and methods are directed to training a machine learning model and for preventing leakage of training data by the machine learning model subsequent to training. A processor is configured to convert a sparse dataset into a matrix of plural data coordinates, generate a priority queue populated with the plural data coordinates, and iteratively select a data coordinate from the priority queue. Plural model values are calculated such that any zero value in the sparse dataset is avoided while maintaining a same result. A next feature is selected, and its weight is altered. Plural variables of the matrix are updated based on the altered weight value, and the priority queue is updated to adjust a priority of the data coordinates based on the update to the plural variables. The process is repeated for each next data coordinate until the model converges to a solution based on the model weights.

公开(公告)号：US11734574B1

公开(公告)日：2023-08-22

申请号：US17689185

申请日：2022-03-08

Applicant: Booz Allen Hamilton Inc.

Inventor： Fred Sun Lu ,  Edward Simon Paster Raff

IPC: G06N3/084 ,  G06N3/048

CPC classification number: G06N3/084 ,  G06N3/048

Abstract: A method, system, and computer program product for configuring a computer for data similarity determination using Bregman divergence may include storing a data set having plural data pairs with one or more data points corresponding to one or more features and generating a trained input convex neural network (ICNN) using the data set, the ICNN having one or more parameters. Training the ICNN may include extracting one or more features for each piece of data in the first data pair, generating an empirical Bregman divergence for the first data pair, and computing one or more gradients between the one or more features within the first data pair using known target distances and the computed empirical Bregman divergence.