Hrl Laboratories, LLC

The Boeing Company

Raytheon Company

Gm Global Technolgoy Operations, Inc.

Hughes Electronics Corporation

Hughes Aircraft Company

Other

David W Payton

Heiko Hoffmann

Michael D Howard

Michael J Daily

Ryan M Uhlenbrock

Craig A Lee

Mike Howard

Qin Jiang

Soheil Kolouri

Adour Vahe Kabakian

Matthew E Phillips

Matthias Ziegler

Mike Daily

Vincent De Sapio

Leandro G Barajas

Rashmi N Sundareswara

Brian N Limketkai

Bruce Hoff

Li Yang Ku

Kyungnam Kim

Yang Chen

Rajan Bhattacharyya

Charles E Martin

Kang-Yu Ni

Suhas E Chelian

Hyukseong Kwon

Chong Ding

Zhichao Chen

Joshua Haug

Kangyu Ni

Yuri Owechko

Tsai-Ching Lu

Swarup S Medasani

Praveen K Pilly

Karim El Defrawy

Jiejun Xu

Aleksey Nogin

Kevin R Martin

William B Noble

Timothy D Smith

Joshua W Baron

Regina Inez Estkowski

Jason Meltzer

Darren J Earl

Peter Allmond Tinker

Karl Paul Dockendorf

Derek W Mitchell

Scott D G Smith

Wendell Bradshaw

Serdar N Gokcen

Eric Martinson

Cory W Peichel

Eric B Martinson

David M Keirsey

Michael Howard

Timothy Smith

A method for synthetic aperture radar (SAR) phase history extraction includes receiving, at a SAR system, a set of SAR phase history data derived from a plurality of return signals, the plurality of return signals produced by the SAR system illuminating a scene with a plurality of radar pulses. A region of interest (ROI) is obtained, the ROI corresponding to a moving target within the scene. A doppler shift frequency range for the moving target is determined based at least in part on an azimuth angle spread corresponding to the ROI and a known approximate trajectory of the moving target. The SAR phase history data is filtered to give extracted phase history corresponding to the moving target based at least in part on the doppler shift frequency range.

Phase history extraction for moving target

Described is a method for extraction of a region of interest (ROI) from a composite synthetic aperture radar (SAR) phase history data. The method comprising receiving, with a system comprising a processor, the composite SAR phase history data of a plurality of backscattered return signals produced by a SAR system illuminating a scene with a SAR beam. The method also comprises obtaining a location of a first ROI within the scene and extracting from the composite SAR phase history data a first component SAR phase history data corresponding to the ROI at the location of the ROI.

System for extraction of a region of interest (ROI) from a composite synthetic aperture radar (SAR) system phase history

Disclosed is a synthetic aperture radar (SAR) system for target recognition with complex range profile. The SAR system comprising a memory, a recurrent neural network (RNN), a multi-layer linear network in signal communication the RNN, and a machine-readable medium on the memory. The machine-readable medium is configured to store instructions that, when executed by the RNN, cause the SAR system to perform various operations. The various operation comprise: receiving raw SAR data associated with observed views of a scene, wherein the raw SAR data comprises information captured via the SAR system; radio frequency (RF) preprocessing the received raw SAR data to produce a processed raw SAR data; converting the processed raw SAR data to a complex SAR range profile data; processing the complex SAR range profile data with the RNN having RNN states; and mapping the RNN states to a target class with the multi-layer linear network.

Complex recurrent neural network for Synthetic Aperture Radar (SAR) target recognition

A computing system including a processor configured to train a synthetic aperture radar (SAR) classifier neural network. The SAR classifier neural network is trained at least in part by, at a SAR encoder, receiving training SAR range profiles that are tagged with respective first training labels, and, at an image encoder, receiving training two-dimensional images that are tagged with respective second training labels. Training the SAR classifier neural network further includes, at a shared encoder, computing shared latent representations based on the SAR encoder outputs and the image encoder outputs, and, at a classifier, computing respective classification labels based on the shared latent representations. Training the SAR classifier neural network further includes computing a value of a loss function based on the plurality of first training labels, the plurality of second training labels, and the plurality of classification labels and performing backpropagation based on the value of the loss function.

Synthetic aperture radar classifier neural network

Described is a system for object detection that is robust to adversarial attacks. An initial hypothesis of an identity of an object in an input image is generated using a sparse convolutional neural network (CNN) and a distribution aware classifier. A foveated hypothesis verification process is performed for identifying a region of the input image that supports the initial hypothesis. Using a part-based classifier, an identity of a part of the object in the region of the input image is predicted. An attack probability for the predicted identity of the part, and the initial hypothesis is updated based on the predicted identity of the part and the attack probability. The foveated hypothesis verification process and updating of hypotheses is performed until a hypothesis reaches a certainty threshold. The object is labeled based on the hypothesis that reached the certainty threshold.

Process to make machine object detection robust to adversarial attacks

Described is a system for side-channel based detection of cyber-attack. In operation, the system converts data bus signals from a platform (e.g., vehicular platform) into a first time series of system states. The system further converts analog side-channel signals from the platform into a second time-series of system states. Anomalous behavior of the platform is detected by comparing the first time series of system states with the second time series of system states to identify violations of predetermined constraints. Upon detection, the anomalous behavior is designated as a cyber-attack of the platform, which causes the platform to initiate an action based on the detected cyber-attack. Such actions include implementing a safe made, etc.

System and method for side-channel based detection of cyber-attack

A method of identifying a target from synthetic aperture radar (SAR) data without incurring the computational load associated with generating an SAR image. The method includes receiving SAR data collected by a radar system including RF phase history data associated with reflected RF pulses from a target in a scene, but excluding an SAR image. Range profile data is determined from the SAR data by converting the RF phase history data into a structured temporal array that can be applied as input to a classifier incorporating a recurrent neural network, such as a recurrent neural network made up of long short-term memory (LSTM) cells that are configured to recognize temporal or spatial characteristics associated with a target, and provide an identification of a target based on the recognized temporal or spatial characteristic.

Target recognition from SAR data using range profiles and a long short-term memory (LSTM) network

A system for cyber-attack detection within cyber-physical systems (such as a vehicle). The system operates by obtaining a time-varying analog side-channel signal from components with the cyber-physical system and converting the time-varying analog side-channel signal to a digital side-channel signal. A time-series of system states are then identified based on the digital side-channel signal. The time-series of system states are compared with software states as generated by the cyber-physical system components, such that when the software states are unmatched with the time-series of system states, a side-channel is designated as having a security breach. In such an event, the cyber-physical system is then caused to implement an action based on the side-channel security breach.

System and method for cyber attack detection based on rapid unsupervised recognition of recurring signal patterns

A tracking system for tracking a moving target includes a processor and a tracking module that implements an iterative process for tracking the moving target. The iterative process includes receiving sensor data for a current state of the moving target. The process also includes applying a filter engine to the sensor data and a measure of error of a previous prediction of the current state of the target to produce a first estimate for an upcoming state and a first measure of error thereof. The process also includes receiving from at least one second tracking system, at least one second estimate for the upcoming state and second measure of error thereof. The process further includes defining a consensus estimate for the upcoming state and a consensus measure of error thereof using the first estimate and the at least one second estimate and the first and second measure of error thereof.

Tracking a target using multiple tracking systems

Described is system for mapping user behavior to brain regions of interest. Using a cognitive-behavior model, a behavioral task is selected that is suited for a desired brain state. Using a functional-anatomical model coupled to the cognitive-behavior model, a set of high-definition neurostimulations is selected to be applied to the user during performance of the selected behavioral task. The selected set of high-definition neurostimulations targets specific regions of the user's brain. Changes in the user's brain state are sensed during application of the set of high-definition neurostimulations and performance of the selected behavioral task using at least one brain monitoring technique. The coupled functional-anatomical and cognitive-behavior models are adapted until the desired brain state is reached.

Thinking cap: combining personalized, model-driven, and adaptive high definition trans-cranial stimulation (HD-tCS) with functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG) brain state measurement and feedback

Described is an inference circuit for pattern recognition for use within convolutional neural nets for online learning using K-means clustering. The inference circuit includes a set of templates, each template having a template data memory. The inference circuit also include at least one match element, the match element being operable for receiving an input data pattern and determining a degree of match between the input data pattern and a template. A best match logic circuit is included for selecting a template in the set of templates that best matches the input data pattern, said template being a best match template. Finally, an updated is included for probabilistically modifying the template data memories based on the best match template.

Inference circuit for improving online learning

Described is a system for secure database searching. The system comprises a client-server architecture which allows a client to securely search a database of records possessed by a server. A database query is generated by the client and transmitted to the server. The database query is processed by the server using a privacy-preserving search protocol. An encrypted match result is produced by the server without decrypting the database query. The encrypted match result is sent to the client, and the client decrypts the encrypted match result to obtain a set of block identifiers representing blocks of records in the database that match the database query. The client obtains a block of encrypted records containing match results using only the set of block identifiers. The match results are decrypted by the client using a key obtained from the server. The unencrypted match results to the database query are then output.

STAGS: secure, tunable, and accountable generic search in databases

An apparatus is provided for tracking a target moving between states using an iterative process. The apparatus receives sensor data for a current state i, and applies a cubature information filter and an H-infinity filter thereto to respectively produce an estimate for the upcoming state i+1 and a measure of error thereof, and adjust the measure of error. The apparatus then defines a consensus estimate of the upcoming state i+1 and a consensus adjusted measure of error thereof from the estimate and adjusted measure of error, and a second estimate and second adjusted measure of error that is received from at least one second apparatus tracking the target. The apparatus then applies a cubature information filter to the consensus estimate of the upcoming state i+1 and the consensus adjusted measure of error to predict the upcoming state i+1.

Tracking a target moving between states in an environment

Described is a system for self-organized critical image segmentation. During operation, the system generates a delta pattern from a self-organized critical process. An initial test pattern is then altered based on the delta pattern to generate a new test pattern. The new test pattern is a mask identifying distinct regions in an image. A new energy score is then generated of the new test pattern. The operations of generating the delta pattern and altering the initial test pattern are then repeated until an energy score of the new test pattern is less than an energy score of the initial test pattern. At that point, the initial test pattern is replaced with the new test pattern. Finally, the process is repeated until a termination condition is reached, at which point the new test pattern provides the image segmentation by dividing the image into distinct regions, including a foreground and background.

System and method for self-organized critical image segmentation

Described is a system for detecting cyber intrusions based on analysis of network traffic. During operation, the system performs a statistical analysis of message timing on network traffic to produce a temporal dependency matrix representative of temporal dependency between different message types in the network traffic. The sets of temporal dependency matrices are decomposed into component matrices, where at least one component matrix represents typical properties of these matrices and at least one other component matrix represents atypical properties of the matrices. A new temporal dependency matrix is generated based on new network traffic. Finally, anomalous behavior is detected in the new network traffic by comparing component matrices of the new temporal dependency matrix with component matrices of the temporal dependency matrices under normal operation conditions.

System for anomaly detection on CAN bus data with sparse and low rank decomposition of transfer entropy matrix

Growing community of inventors

Calabasas, CA, United States of America

David W Payton