公开(公告)号：US20230074968A1

公开(公告)日：2023-03-09

申请号：US17404160

申请日：2021-08-17

Applicant: Northrop Grumman Systems Corporation

Inventor： Benjamin C. Gookin ,  Nathanael M. Harmon ,  Justin Kopacz ,  Michael Herndon

IPC: G06N3/08 ,  G06K9/62

Abstract: Classification of signals using machine learning and related systems, methods and computer-readable media are disclosed. A signal classification system includes a sentence embedding model network, a convolutional generator network, and a classifier network. The sentence embedding model network is trained to convert a body of sentences correlated to different signal modulation schemes into a latent space. The convolutional generator network is configured to project samples of a measured signal into the latent space. The classifier network is configured to classify the measured signal from the latent space responsive to a projection of the samples of the measured signal into the latent space. A method includes training a sentence embedding model network to convert descriptive sentences to a latent space, the descriptive sentences correlated to different signal modulation schemes. The method also includes training a convolutional generator network to project samples of a measured signal into the latent space.

公开(公告)号：US12189742B2

公开(公告)日：2025-01-07

申请号：US17666353

申请日：2022-02-07

Applicant: Northrop Grumman Systems Corporation

Inventor： Benjamin C. Gookin ,  David Domico ,  Justin Kopacz ,  Matthew D. Popovich ,  Michelle Jin ,  Nathanael M. Harmon

IPC: G06F21/32 ,  G06N3/084 ,  G06V10/44 ,  G06V40/12 ,  H04W12/062 ,  H04W12/10 ,  H04W12/69

Abstract: The present disclosure is directed toward systems and methods for fingerprinting wireless communications using few-shot learning techniques. The systems and methods relate to storing fingerprint data indicating device fingerprint features detected for a plurality of identified transmitting devices in a database. The methods further relate to receiving, at a communication device, wireless communications from an unidentified transmitting device. Additionally, the systems and methods illustrate determining a device fingerprint responsive to a portion of each of the wireless communications using few-shot learning techniques and comparing the determined device fingerprint to the stored fingerprint data in the database.

公开(公告)号：US20230252118A1

公开(公告)日：2023-08-10

申请号：US17666353

申请日：2022-02-07

Applicant: Northrop Grumman Systems Corporation

Inventor： Benjamin C. Gookin ,  David Domico ,  Justin Kopacz ,  Matthew D. Popovich ,  Michelle Jin ,  Nathanael M. Harmon

IPC: G06F21/32 ,  G06V10/44 ,  G06V40/12 ,  H04W12/10 ,  H04W12/062 ,  G06N3/08 ,  H04W12/69

CPC classification number: G06F21/32 ,  G06V10/454 ,  G06V40/12 ,  H04W12/10 ,  H04W12/062 ,  G06N3/084 ,  H04W12/69

Abstract: The present disclosure is directed toward systems and methods for fingerprinting wireless communications using few-shot learning techniques. The systems and methods relate to storing fingerprint data indicating device fingerprint features detected for a plurality of identified transmitting devices in a database. The methods further relate to receiving, at a communication device, wireless communications from an unidentified transmitting device. Additionally, the systems and methods illustrate determining a device fingerprint responsive to a portion of each of the wireless communications using few-shot learning techniques and comparing the determined device fingerprint to the stored fingerprint data in the database.