公开(公告)号：US20180278425A1

公开(公告)日：2018-09-27

申请号：US15469667

申请日：2017-03-27

Applicant: Intelligent Fusion Technology, Inc

Inventor： Yiran XU ,  Gang WANG ,  Sixiao WEI ,  Genshe CHEN ,  Khanh PHAM ,  Erik BLASCH

IPC: H04L9/32 ,  H04W28/04 ,  H04L29/06

Abstract: Methods and systems for cyber secure data communications are provided. In some embodiments, a method for transmitting data comprises: performing a marker-based data encoding process to embed a digital watermark into each of a plurality of original data flows to be transmitted to a plurality of receivers; performing a non-orthogonal multiple access process to allocate transmission powers to the plurality of original data flows, such that the plurality of original data flows are simultaneously superposed on a carrier frequency to generate a superposed signal; performing a noise modulation process to modulate the superposed signal to generate a noise-like signal and a reference noise signal; transmitting the noise-like signal and the reference noise signal through orthogonally polarized antennas; and performing a portal-based data integrity analysis process to check whether a receiver in the plurality of receivers is compromised or manipulated.

公开(公告)号：US20230315851A1

公开(公告)日：2023-10-05

申请号：US17707277

申请日：2022-03-29

Applicant: Intelligent Fusion Technology, Inc.

Inventor： Sixiao WEI ,  Genshe CHEN ,  Kuochu CHANG ,  Thomas M. CLEMONS, III

IPC: G06F21/56 ,  G06N7/00

CPC classification number: G06F21/566 ,  G06N7/005 ,  G06F2221/034

Abstract: A method for detecting false data injection attacks (FDIAs) on a condition-based predictive maintenance (CBPM) system includes: collecting sensor data from sensors monitoring components of a system maintained by the CBPM system to extract features for a cyberattack detection model and gathering historical data of the system to build a cyberattack knowledge base about the system; combining the sensor data and the historical data to train the cyberattack detection model; using a graphical Bayesian network model to capture domain knowledge and condition-symptom relationships between the sensor-monitored components and the sensors; and based on the cyberattack detection model and the Bayesian network model, detecting the FDIAs on the CBPM system.

公开(公告)号：US20220085878A1

公开(公告)日：2022-03-17

申请号：US17021289

申请日：2020-09-15

Applicant: INTELLIGENT FUSION TECHNOLOGY, INC.

Inventor： Lun LI ,  Yi LI ,  Sixiao WEI ,  Dan SHEN ,  Genshe CHEN

IPC: H04B10/077 ,  G06N3/04 ,  H04B10/11 ,  G06K9/62 ,  G06N3/08

Abstract: Various embodiments provide a method for free space optical communication performance prediction method. The method includes: in a training stage, collecting a large number of data representing FSOC performance from external data sources and through simulation in five feature categories; dividing the collected data into training datasets and testing datasets to train a prediction model based on a deep neural network (DNN); evaluating a prediction error by a loss function and adjusting weights and biases of hidden layers of the DNN to minimize the prediction error; repeating training the prediction model until the prediction error is smaller than or equal to a pre-set threshold; in an application stage, receiving parameters entered by a user for an application scenario; retrieving and preparing real-time data from the external data sources for the application scenario; and generating near real-time FSOC performance prediction results based on the trained prediction model.