Benjamin J Edwards

US Patent:

20210333114, Oct 28, 2021

Filed:

Apr 27, 2021

Appl. No.:

17/241559

Inventors:

- Medina MN, US
Stacey E. Stewart - Stillwater MN, US
Kevin E. Nelson - Osceola WI, US
Joseph P. Nuxoll - San Jose CA, US
Cindy L. Houeiss - Kasson MN, US
Benjamin T. Edwards - Roseau MN, US
Joseph D. Tharaldson - Taylor Falls MN, US
Andrew C. Schmid - Brooklyn Park MN, US
Elaine M. Scott - San Francisco CA, US
Brenden Bungert - Chisago City MN, US

International Classification:

G01C 21/34
G01C 21/36
G01W 1/10

Abstract:

Systems and methods for dynamically planning a travel route using weather data for a recreational vehicle, dynamically navigating around inclement weather for a recreational vehicle, for dynamic fuel range mapping for a recreational vehicle, and/or for predicting a departure time to arrive at a destination on time for a recreational vehicle are disclosed.

US Patent:

20210150042, May 20, 2021

Filed:

Nov 15, 2019

Appl. No.:

16/685474

Inventors:

- Armonk NY, US
Frederico Araujo - White Plains NY, US
Teryl Taylor - Danbury CT, US
Marc Phillipe Stoecklin - White Plains NY, US
Benjamin James Edwards - Ossining NY, US
Ian Michael Molloy - Westchester NY, US

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 21/62
H04L 9/08
G06F 17/16
G06N 20/00

Abstract:

A neural network is trained using a training data set, resulting in a set of model weights, namely, a matrix X, corresponding to the trained network. The set of model weights is then modified to produce a locked matrix X′, which is generated by applying a key. In one embodiment, the key is a binary matrix {0, 1} that zeros (masks) out certain neurons in the network, thereby protecting the network. In another embodiment, the key comprises a matrix of sign values {−1, +1}. In yet another embodiment, the key comprises a set of real values. Preferably, the key is derived by applying a key derivation function to a secret value. The key is symmetric, such that the key used to protect the model weight matrix X (to generate the locked matrix) is also used to recover that matrix, and thus enable access to the model as it was trained.

US Patent:

20200050945, Feb 13, 2020

Filed:

Aug 7, 2018

Appl. No.:

16/057706

Inventors:

- Armonk NY, US
Wilka Carvalho - Los Angeles CA, US
Heiko H. Ludwig - San Francisco CA, US
Ian Michael Molloy - Chappaqua NY, US
Taesung Lee - Ridgefield CT, US
Jialong Zhang - White Plains NY, US
Benjamin J. Edwards - Ossining NY, US

International Classification:

G06N 3/08
G06N 3/04

Abstract:

One embodiment provides a method comprising receiving a training set comprising a plurality of data points, where a neural network is trained as a classifier based on the training set. The method further comprises, for each data point of the training set, classifying the data point with one of a plurality of classification labels using the trained neural network, and recording neuronal activations of a portion of the trained neural network in response to the data point. The method further comprises, for each classification label that a portion of the training set has been classified with, clustering a portion of all recorded neuronal activations that are in response to the portion of the training set, and detecting one or more poisonous data points in the portion of the training set based on the clustering.

US Patent:

20190318099, Oct 17, 2019

Filed:

Apr 16, 2018

Appl. No.:

15/953956

Inventors:

- Armonk NY, US
Bryant Chen - San Jose CA, US
Benjamin J. Edwards - Ossining NY, US
Taesung Lee - Ridgefield CT, US
Ian M. Molloy - Chappaqua NY, US
Jialong Zhang - White Plains NY, US

International Classification:

G06F 21/57
G06N 3/08
G06N 99/00

Abstract:

Mechanisms are provided for evaluating a trained machine learning model to determine whether the machine learning model has a backdoor trigger. The mechanisms process a test dataset to generate output classifications for the test dataset, and generate, for the test dataset, gradient data indicating a degree of change of elements within the test dataset based on the output generated by processing the test dataset. The mechanisms analyze the gradient data to identify a pattern of elements within the test dataset indicative of a backdoor trigger. The mechanisms generate, in response to the analysis identifying the pattern of elements indicative of a backdoor trigger, an output indicating the existence of the backdoor trigger in the trained machine learning model.

US Patent:

20190199731, Jun 27, 2019

Filed:

Dec 22, 2017

Appl. No.:

15/851852

Inventors:

- Armonk NY, US
Taesung Lee - Ridgefield CT, US
Ian M. Molloy - Chappaqua NY, US
Suresh Chari - Scarsdale NY, US
Benjamin J. Edwards - Ossining NY, US

International Classification:

H04L 29/06
G06F 17/30

Abstract:

Jointly discovering user roles and data clusters using both access and side information by performing the following operation: (i) representing a set of users as respective vectors in a user feature space; representing data as respective vectors in a data feature space; (ii) providing a user-data access matrix, in which each row represents a user's access over the data; and (iii) co-clustering the users and data using the user-data matrix to produce a set of co-clusters.

US Patent:

20180359270, Dec 13, 2018

Filed:

Jun 12, 2017

Appl. No.:

15/619598

Inventors:

- Armonk NY, US
Benjamin Edwards - Yorktown Heights NY, US
Taesung Lee - White Plains NY, US
Ian M. Molloy - Chappaqua NY, US

International Classification:

H04L 29/06

Abstract:

Detecting anomalous user behavior is provided. User activity is logged for a set of users. The user activity is divided into distinct time intervals. For each distinct time interval, logged user activity is converted to a numerical representation of each user's activities for that distinct time interval. A clustering process is used on the numerical representations of user activities to determine which users have similar activity patterns in each distinct time interval. A plurality of peer groups of users is generated based on determining the similar activity patterns in each distinct time interval. Anomalous user behavior is detected based on a user activity change in a respective peer group of users within a distinct time interval.