公开(公告)号：US20250039210A1

公开(公告)日：2025-01-30

申请号：US18912009

申请日：2024-10-10

Applicant: L3Harris Technologies, Inc.

Inventor： Mark Rahmes ,  Kevin Fox ,  Robert Konczynski ,  Ziad Chaudhry ,  Kusay Rukieh ,  Jody Flieder ,  Macaulay Osaisai

IPC: H04L9/40 ,  G06N7/01

Abstract: Network security anomaly detection systems and methods include a processor, in communication with the network, receiving network device status information. A variational autoencoder receives the device status information, optimizes the device status information, and determines whether the device status information qualifies as an anomaly. Optimized device status information is compared to either non-anomalous or anomalous device status data in a latent space of the variational autoencoder. The latent space preferably includes an n-D point scatter plot and hidden vector values. The processor optimizes the device status information by generating a plurality of probabilistic models of the device status information and determining which of the plurality of models is optimal. A game theoretic optimization is applied to the plurality of models, and the best model is used to generate the n-D point scatter plot in latent space. An image gradient sobel edge detector preprocesses the device status information prior to optimization.

公开(公告)号：US12190525B2

公开(公告)日：2025-01-07

申请号：US17552074

申请日：2021-12-15

Applicant: L3Harris Technologies, Inc.

Inventor： Mark Rahmes ,  Jennifer Spicer ,  Robert Konczynski ,  Kusay Rukieh ,  Jody Flieder ,  Dustin Ellsworth ,  Michael Fischer ,  Timothy Bruce Faulkner

IPC: G06V10/26 ,  G06T7/13 ,  G06V10/44 ,  G06V10/46 ,  G08G5/00

Abstract: Systems and methods for detecting anomalies in aviation data communication systems (e.g., air traffic control surveillance systems), include a processor receiving device status information. A variational autoencoder receives and optimizes the device status information and determines whether it qualifies as an anomaly. Optimized device status information is compared to either non-anomalous or anomalous device status data in a latent space of the variational autoencoder. The latent space preferably includes an n-D point scatter plot and hidden vector values. The processor optimizes the device status information by generating a plurality of probabilistic models of the device status information and determining which of the plurality of models is optimal. A game theoretic optimization is applied to the plurality of models, and the best model is used to generate the n-D point scatter plot in latent space. An image gradient sobel edge detector preprocesses the device status information prior to optimization.

公开(公告)号：US20230186482A1

公开(公告)日：2023-06-15

申请号：US17552074

申请日：2021-12-15

Applicant: L3Harris Technologies, Inc.

Inventor： Mark Rahmes ,  Jennifer Spicer ,  Robert Konczynski ,  Kusay Rukieh ,  Jody Flieder ,  Dustin Ellsworth ,  Michael Fischer ,  Timothy Bruce Faulkner

IPC: G06T7/13 ,  G06V10/44 ,  G06V10/46 ,  G06V10/26 ,  G08G5/00

CPC classification number: G06T7/13 ,  G06V10/457 ,  G06V10/462 ,  G06V10/476 ,  G06V10/26 ,  G08G5/0004 ,  G08G5/0073 ,  G06T2207/10028

Abstract: Systems and methods for detecting anomalies in aviation data communication systems (e.g., air traffic control surveillance systems), include a processor receiving device status information. A variational autoencoder receives and optimizes the device status information and determines whether it qualifies as an anomaly. Optimized device status information is compared to either non-anomalous or anomalous device status data in a latent space of the variational autoencoder. The latent space preferably includes an n-D point scatter plot and hidden vector values. The processor optimizes the device status information by generating a plurality of probabilistic models of the device status information and determining which of the plurality of models is optimal. A game theoretic optimization is applied to the plurality of models, and the best model is used to generate the n-D point scatter plot in latent space. An image gradient sobel edge detector preprocesses the device status information prior to optimization.

公开(公告)号：US12149550B2

公开(公告)日：2024-11-19

申请号：US17545594

申请日：2021-12-08

Applicant: L3Harris Technologies, Inc.

Inventor： Mark Rahmes ,  Kevin Fox ,  Robert Konczynski ,  Ziad Chaudhry ,  Kusay Rukieh ,  Jody Flieder ,  Macaulay Osaisai

IPC: G06F21/00 ,  G06N7/01 ,  H04L9/40

Abstract: Network security anomaly detection systems and methods include a processor, in communication with the network, receiving network device status information. A variational autoencoder receives the device status information, optimizes the device status information, and determines whether the device status information qualifies as an anomaly. Optimized device status information is compared to either non-anomalous or anomalous device status data in a latent space of the variational autoencoder. The latent space preferably includes an n-D point scatter plot and hidden vector values. The processor optimizes the device status information by generating a plurality of probabilistic models of the device status information and determining which of the plurality of models is optimal. A game theoretic optimization is applied to the plurality of models, and the best model is used to generate the n-D point scatter plot in latent space. An image gradient sobel edge detector preprocesses the device status information prior to optimization.

公开(公告)号：US20230244915A1

公开(公告)日：2023-08-03

申请号：US17591897

申请日：2022-02-03

Applicant: L3Harris Technologies, Inc.

Inventor： Mark Rahmes ,  Kevin Fox ,  Jennifer Spicer ,  Shoaib Shaikh ,  Macaulay Osaisai ,  Michael Fischer ,  Ziad Chaudhry

IPC: G06N3/04 ,  G06N3/08 ,  G06V10/82

CPC classification number: G06N3/0472 ,  G06N3/088 ,  G06V10/82

Abstract: Methods of training a variational autoencoder (VAE) to recognize anomalous data in a distributed system are provided. Input image data representative of devices/processes in a distributed system are provided to an encoder of a VAE on a processor. The input image data is compressed, via the processor, using a first plurality of weights with the encoder. A normal distribution of the compressed image data is created in a latent space of the VAE. The compressed image data from the latent space is decompressed using a second plurality of weights with a decoder of the VAE. The decompressed image data from the decoder is optimized. At least the first and second plurality of weights are updated, via the processor, based on the loss detected in the optimized decompressed image data. The above steps are iterated until the decompressed image data possesses substantially the same statistical properties as the input image data.

公开(公告)号：US20230179616A1

公开(公告)日：2023-06-08

申请号：US17545594

申请日：2021-12-08

Applicant: L3Harris Technologies, Inc.

Inventor： Mark Rahmes ,  Kevin Fox ,  Robert Konczynski ,  Ziad Chaudhry ,  Kusay Rukieh ,  Jody Flieder ,  Macaulay Osaisai

IPC: G06N7/00

CPC classification number: H04L63/1425 ,  G06N7/005

Abstract: Network security anomaly detection systems and methods include a processor, in communication with the network, receiving network device status information. A variational autoencoder receives the device status information, optimizes the device status information, and determines whether the device status information qualifies as an anomaly. Optimized device status information is compared to either non-anomalous or anomalous device status data in a latent space of the variational autoencoder. The latent space preferably includes an n-D point scatter plot and hidden vector values. The processor optimizes the device status information by generating a plurality of probabilistic models of the device status information and determining which of the plurality of models is optimal. A game theoretic optimization is applied to the plurality of models, and the best model is used to generate the n-D point scatter plot in latent space. An image gradient sobel edge detector preprocesses the device status information prior to optimization.

公开(公告)号：US20250054159A1

公开(公告)日：2025-02-13

申请号：US18933733

申请日：2024-10-31

Applicant: L3Harris Technologies, Inc.

Inventor： Mark Rahmes ,  Jennifer Spicer ,  Robert Konczynski ,  Kusay Rukieh ,  Jody Flieder ,  Dustin Ellsworth ,  Michael Fischer ,  Timothy Bruce Faulkner

IPC: G06T7/13 ,  G06V10/26 ,  G06V10/44 ,  G06V10/46 ,  G08G5/00

Abstract: Systems and methods for detecting anomalies in aviation data communication systems (e.g., air traffic control surveillance systems), include a processor receiving device status information. A variational autoencoder receives and optimizes the device status information and determines whether it qualifies as an anomaly. Optimized device status information is compared to either non-anomalous or anomalous device status data in a latent space of the variational autoencoder. The latent space preferably includes an n-D point scatter plot and hidden vector values. The processor optimizes the device status information by generating a plurality of probabilistic models of the device status information and determining which of the plurality of models is optimal. A game theoretic optimization is applied to the plurality of models, and the best model is used to generate the n-D point scatter plot in latent space. An image gradient sobel edge detector preprocesses the device status information prior to optimization.