公开(公告)号：US11265305B2

公开(公告)日：2022-03-01

申请号：US16509949

申请日：2019-07-12

Applicant: International Business Machines Corporation

Inventor： Jeb R. Linton ,  Naeem Altaf ,  Sanjay Nadhavajhala ,  Satya Sreenivas

IPC: H04L29/06 ,  H04L41/12 ,  H04L9/30 ,  H04L67/12

Abstract: Managing anonymous network connections. In one aspect managing anonymous network connections by providing anonymous authentication credentials to a plurality of devices in a hierarchical network, registering a first set of devices at a first data aggregator, determining that the first set of devices at the first aggregator numbers less than a first threshold value, registering the first set of devices with a second aggregator upstream in the hierarchy from the first aggregator, causing data from the first set of devices to be received at the second aggregator.

公开(公告)号：US11138781B1

公开(公告)日：2021-10-05

申请号：US16837573

申请日：2020-04-01

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Jeb R. Linton ,  Satya Sreenivas ,  Naeem Atlaf ,  Sanjay Nadhavajhala

IPC: G06T13/40 ,  G06T3/40 ,  G06N3/08 ,  G10L13/027 ,  G06T17/20

Abstract: A computer-implemented method for the automatic generation of photorealistic 3D avatars. The method includes generating, using machine learning network, a plurality of 2D photorealistic facial images; generating, using a model agnostic meta-learner, a plurality of 2D photorealistic facial expression images based on the plurality of 2D photorealistic facial images; and generating a plurality of 3D photorealistic avatars based on the plurality of 2D photorealistic facial expression images.

公开(公告)号：US20210014209A1

公开(公告)日：2021-01-14

申请号：US16509949

申请日：2019-07-12

Applicant: International Business Machines Corporation

Inventor： Jeb R. Linton ,  Naeem Altaf ,  Sanjay Nadhavajhala ,  Satya Sreenivas

IPC: H04L29/06 ,  H04L9/30 ,  H04L12/24

Abstract: Managing anonymous network connections. In one aspect managing anonymous network connections by providing anonymous authentication credentials to a plurality of devices in a hierarchical network, registering a first set of devices at a first data aggregator, determining that the first set of devices at the first aggregator numbers less than a first threshold value, registering the first set of devices with a second aggregator upstream in the hierarchy from the first aggregator, causing data from the first set of devices to be received at the second aggregator.

公开(公告)号：US11665180B2

公开(公告)日：2023-05-30

申请号：US16804898

申请日：2020-02-28

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Jeb R. Linton ,  Darrel Haswell ,  Satya Sreenivas ,  Naeem Altaf ,  Sanjay Nadhavajhala ,  Ron Williams ,  Bradley Evan Harris ,  John Walter Morris

IPC: H04L29/06 ,  G06N3/08 ,  G06K9/62 ,  H04L9/40 ,  G06N3/088 ,  G06F18/214

CPC classification number: H04L63/1416 ,  G06F18/2155 ,  G06N3/088 ,  H04L63/1425

Abstract: Methods and systems for artificially intelligent security incident and event management using an attention-based deep neural network and transfer learning are disclosed. A method includes: collecting, by a computing device, system and network activity events in bulk; forming, by the computing device, a corpus using the collected system and network activity events; correlating, by the computing device, discrete events of the system and network activity events into offenses; adding, by the computing device, additional features to the corpus representing the offenses and disposition decisions regarding the offenses; training, by the computing device, a deep neural network using the corpus; and tuning, by the computing device, the deep neural network for a monitored computing environment using transfer learning.

公开(公告)号：US20210312683A1

公开(公告)日：2021-10-07

申请号：US16837573

申请日：2020-04-01

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Jeb R. Linton ,  Satya Sreenivas ,  Naeem Atlaf ,  Sanjay Nadhavajhala

IPC: G06T13/40 ,  G06T3/40 ,  G06T17/20 ,  G10L13/027 ,  G06N3/08

Abstract: A computer-implemented method for the automatic generation of photorealistic 3D avatars. The method includes generating, using machine learning network, a plurality of 2D photorealistic facial images; generating, using a model agnostic meta-learner, a plurality of 2D photorealistic facial expression images based on the plurality of 2D photorealistic facial images; and generating a plurality of 3D photorealistic avatars based on the plurality of 2D photorealistic facial expression images.