公开(公告)号：US11934520B2

公开(公告)日：2024-03-19

申请号：US16368589

申请日：2019-03-28

Applicant: Nvidia Corporation

Inventor： Gorkem Batmaz ,  Nicola DiMiscio ,  Mark Overby ,  Ildiko Pete

IPC: G06N3/08 ,  G06F11/30 ,  G06F11/34 ,  G06F21/55 ,  G06F21/85 ,  G06N3/044 ,  G06N3/045 ,  G06N3/088 ,  G06N5/045 ,  G06N7/01 ,  H04L9/40 ,  H04L12/40 ,  H04L67/12

CPC classification number: G06F21/552 ,  G06F11/3027 ,  G06F11/349 ,  G06F21/554 ,  G06F21/556 ,  G06F21/85 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06N3/088 ,  G06N5/045 ,  G06N7/01 ,  H04L12/40 ,  H04L12/40045 ,  H04L63/1416 ,  H04L63/1441 ,  G06F2221/034 ,  H04L67/12

Abstract: The disclosure provides systems and processes for applying neural networks to detect intrusions and other anomalies in communications exchanged over a data bus between two or more devices in a network. The intrusions may be detected in data being communicated to an embedded system deployed in vehicular or robotic platforms. The disclosed system and process are well suited for incorporation into autonomous control or advanced driver assistance system (ADAS) vehicles including, without limitation, automobiles, motorcycles, boats, planes, and manned and un-manned robotic devices. Data communicated to an embedded system can be detected over any of a variety of data buses. In particular, embodiments disclosed herein are well suited for use in any data communication interface exhibiting the characteristics of a lack of authentication or following a broadcast routing scheme—including, without limitation, a control area network (CAN) bus.

公开(公告)号：US20240098106A1

公开(公告)日：2024-03-21

申请号：US18235213

申请日：2023-08-17

Applicant: NVIDIA Corporation

Inventor： Rachel Allen ,  Gorkem Batmaz ,  Michael Demoret ,  Ryan Kraus ,  Hsin Chen ,  Bartley Richardson

IPC: H04L9/40

CPC classification number: H04L63/1425 ,  H04L63/102 ,  H04L63/104

Abstract: Technologies for generating a set of models for each account, where each model is a fine-grained, unsupervised behavior model trained for each user to monitor and detect anomalous patterns are described. An unsupervised training pipeline can generate user models, each being associated with one of multiple accounts and is trained to detect an anomalous pattern using feature data associated with the one account. Each account is associated with at least one of a user, a machine, or a service. An inference pipeline can detect a first anomalous pattern in first data associated with a first account using a first user model. The inference pipeline can detect a second anomalous pattern in second data associated with a second account using a second user model.

公开(公告)号：US20240314164A1

公开(公告)日：2024-09-19

申请号：US18185578

申请日：2023-03-17

Applicant: Nvidia Corporation

Inventor： Bartley Douglas Richardson ,  Shawn Davis ,  Gorkem Batmaz ,  Rachel Allen

IPC: H04L9/40

CPC classification number: H04L63/1483

Abstract: Approaches in accordance with various illustrative embodiments provide for the generation of synthetic communications for use in training and fine-tuning threat detection models for various categories of recipients. In at least one embodiment, guidelines can be determined for a category of recipient that can be used to generate multiple types of content using generative artificial intelligence (AI), as may include text, image, and file content. A training communication can be generated using these types of content, such as to generate an email message that corresponds to a potential spear phishing attack. The generated messages can be checked for quality, and any messages that are caught by existing filters can be deleted or regenerated so that only high quality examples of spear phishing are provided as output. These training communications can be used to train a spear phishing detector for a specific category of recipient, in order to accurately flag and prevent access to actual spear phishing communications.

公开(公告)号：US20190303567A1

公开(公告)日：2019-10-03

申请号：US16368589

申请日：2019-03-28

Applicant: Nvidia Corporation

Inventor： Gorkem Batmaz ,  Nicola DiMiscio ,  Mark Overby ,  Ildiko Pete

IPC: G06F21/55 ,  G06F11/30 ,  G06F11/34 ,  G06N3/08 ,  G06N7/00

Abstract: The disclosure provides systems and processes for applying neural networks to detect intrusions and other anomalies in communications exchanged over a data bus between two or more devices in a network. The intrusions may be detected in data being communicated to an embedded system deployed in vehicular or robotic platforms. The disclosed system and process are well suited for incorporation into autonomous control or advanced driver assistance system (ADAS) vehicles including, without limitation, automobiles, motorcycles, boats, planes, and manned and un-manned robotic devices. Data communicated to an embedded system can be detected over any of a variety of data buses. In particular, embodiments disclosed herein are well suited for use in any data communication interface exhibiting the characteristics of a lack of authentication or following a broadcast routing scheme—including, without limitation, a control area network (CAN) bus.