公开(公告)号：US20210174213A1

公开(公告)日：2021-06-10

申请号：US17115464

申请日：2020-12-08

Applicant: NEC Laboratories America, Inc.

Inventor： Renqiang Min ,  Christopher Malon ,  Pengyu Cheng

IPC: G06N3/08 ,  G06F40/20

Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing, by a bidirectional Long Short-Term Memory (LSTM) with a multi-head attention mechanism, a dataset including a plurality of pairs each formed from a given one of a plurality of input text structures and given one of a plurality of style labels for the plurality of input text structures. The method further includes training the bidirectional LSTM as an encoder to disentangle a sequential text input into disentangled representations comprising a content embedding and a style embedding based on a subset of the dataset. The method also includes training a unidirectional LSTM as a decoder to generate a next text structure prediction for the sequential text input based on previously generated text structure information and a current word, from a disentangled representation with the content embedding and the style embedding.

公开(公告)号：US20210133080A1

公开(公告)日：2021-05-06

申请号：US17072526

申请日：2020-10-16

Applicant: NEC Laboratories America, Inc.

Inventor： Wei Cheng ,  Shuchu Han ,  Haifeng Chen

IPC: G06F11/34 ,  G06F11/30 ,  G06F11/07

Abstract: Methods and systems for detecting and responding to anomalous system behavior include detecting an anomaly in a cyber-physical system, based on a classification of time series information, from sensors that monitor the cyber-physical system, as being anomalous. A transition rule is extracted from the time series information to characterize a cause of the anomalous behavior, using a temporal gradient boosting tree. A corrective action is performed responsive to the detected anomaly, prioritized by the cause of the anomalous behavior.

公开(公告)号：US10999323B2

公开(公告)日：2021-05-04

申请号：US16101834

申请日：2018-08-13

Applicant: NEC Laboratories America, Inc.

Inventor： Cristian Lumezanu ,  Nipun Arora ,  Haifeng Chen ,  Bo Zong ,  Daeki Cho ,  Mingda Li

IPC: G06F21/00 ,  H04L29/06 ,  H04L12/733 ,  H04L12/26 ,  H04L12/741 ,  G06N20/00 ,  H04L12/751 ,  H04L12/893 ,  G06K9/62 ,  G06N3/08

Abstract: Endpoint security systems and methods include a distance estimation module configured to calculate a travel distance between a source Internet Protocol (IP) address and an IP address for a target network endpoint system from a received packet received by a network gateway system based on time-to-live (TTL) information from the received packet. A machine learning model is configured to estimate an expected travel distance between the source IP address and the target network endpoint system IP address based on a sparse set of known source/target distances. A spoof detection module is configured to determine that the received packet has a spoofed source IP address based on a comparison between the calculated travel distance and the expected travel distance. A security module is configured to perform a security action at the network gateway system responsive to the determination that the received packet has a spoofed source IP address.

公开(公告)号：US10997488B2

公开(公告)日：2021-05-04

申请号：US16825395

申请日：2020-03-20

Applicant: NEC Laboratories America, Inc.

Inventor： Mohammad Khojastepour

IPC: H04Q5/22 ,  G06K19/077 ,  G06K7/10 ,  H01Q1/22 ,  H04W4/35 ,  G06K19/067

Abstract: A product tagging system is provided. The product tagging system includes at least one RF backscatter transmitter configured to emit a Radio Frequency (RF) signal on a frequency. The product tagging system further includes a plurality of passive RF backscatter tags, each associated with a respective product and configured to reflect and frequency shift the RF signal to a respective different frequency. The product tagging system also includes at least one RF backscatter receiver configured to read the respective product on the respective different frequency by detecting a distributed ambient backscatter signal generated by a reflection and frequency shifting of the RF signal by a corresponding one of the plurality of passive RF backscatter tags.

公开(公告)号：US10990616B2

公开(公告)日：2021-04-27

申请号：US15351452

申请日：2016-11-15

Applicant: NEC Laboratories America, Inc.

Inventor： Biplob Debnath ,  Jianwu Xu ,  Hui Zhang ,  Guofei Jiang ,  Hossein Hamooni

IPC: G06F11/34 ,  G06F16/31 ,  G06F17/40 ,  G06K9/46

Abstract: Systems and methods are disclosed for parsing logs from arbitrary or unknown systems or applications by capturing heterogeneous logs from the arbitrary or unknown systems or applications; generating one pattern for every unique log message; building a pattern hierarchy tree by grouping patterns based on similarity metrics, and for every group it generates one pattern by combing all constituting patterns of that group; and selecting a set of patterns from the pattern hierarchy tree.

公开(公告)号：US20210111794A1

公开(公告)日：2021-04-15

申请号：US17106143

申请日：2020-11-29

Applicant: NEC Laboratories America, Inc.

Inventor： Yue-Kai HUANG ,  Shaoliang ZHANG ,  Ezra IP ,  Jiakai YU

IPC: H04B10/079 ,  G06N3/04

Abstract: Aspects of the present disclosure describe systems, methods. and structures in which a hybrid neural network combining a CNN and several ANNs are shown useful for predicting G-ONSR for Ps-256QAM raw data in deployed SSMF metro networks with 0.27 dB RMSE. As demonstrated, the CNN classifier is trained with 80.96% testing accuracy to identify channel shaping factor. Several ANN regression models are trained to estimate G-OSNR with 0.2 dB for channels with various constellation shaping. Further aspects include the tuning of existing optical networks and the characterization of retrofit/upgraded optical networks to estimate capacity—both aspects employing our inventive hybrid neural network methodology.

公开(公告)号：US20210110210A1

公开(公告)日：2021-04-15

申请号：US17128535

申请日：2020-12-21

Applicant: NEC Laboratories America, Inc.

Inventor： Yi-Hsuan Tsai ,  Kihyuk Sohn ,  Buyu Liu ,  Manmohan Chandraker ,  Jong-Chyi Su

IPC: G06K9/62 ,  G06K9/00 ,  G06K9/32 ,  B60W30/095 ,  B60W30/09 ,  B60W10/20 ,  B60W10/18 ,  B60W50/00 ,  G08G1/16 ,  G06N3/08

Abstract: Systems and methods for lane marking and road sign recognition are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes one or more road scenes having lane markings and road signs. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

公开(公告)号：US20210103706A1

公开(公告)日：2021-04-08

申请号：US17060850

申请日：2020-10-01

Applicant: NEC Laboratories America, Inc.

Inventor： Wenchao Yu ,  Bo Zong ,  Wei Cheng ,  Haifeng Chen ,  Xiusi Chen

IPC: G06F40/58 ,  G06F40/44 ,  G06N5/02 ,  G06N5/04 ,  G06N3/04

Abstract: Methods and systems for performing a knowledge graph task include aligning multiple knowledge graphs and performing a knowledge graph task using the aligned multiple knowledge graphs. Aligning the multiple knowledge graphs includes updating entity representations based on representations of neighboring entities within each knowledge graph, updating entity representations based on representations of entities from different knowledge graphs, and learning machine learning model parameters to align the multiple knowledge graphs, based on the updated entity representations.

公开(公告)号：US10943419B2

公开(公告)日：2021-03-09

申请号：US16689663

申请日：2019-11-20

Applicant: NEC Laboratories America, Inc.

Inventor： Mohammad Khojastepour ,  Mustafa Arslan ,  Sampath Rangarajan

IPC: G07C9/00 ,  G07C9/28 ,  H01Q1/12 ,  E06B11/02 ,  G06K7/10 ,  H04W4/80 ,  E06B11/08 ,  G07C9/15 ,  G07C9/27

Abstract: A walk-though gate (WTG) is presented. The WTG includes a WTG structure including a first wall and a second wall, the first and second walls defining a walk though pass way between an entrance and exit, at least one sensor located at the entrance and the exit of a cavity defined by the walk though pass way, at least one first antenna facing toward an inside region of the WTG structure, at least one second antenna facing away from the inside region of the WTG structure, an RFID reader connected to the at least one first and second antennas, and a judgement module to judge if an RFID tag is located inside or outside the walk though gate structure.

公开(公告)号：US20210067558A1

公开(公告)日：2021-03-04

申请号：US17004547

申请日：2020-08-27

Applicant: NEC Laboratories America, Inc.

Inventor： Jingchao Ni ,  Haifeng Chen ,  Bo Zong ,  LuAn Tang ,  Wei Cheng

IPC: H04L29/06 ,  G06N3/04

Abstract: Methods and systems for detecting and responding to anomalous nodes in a network include inferring temporal factors, using a computer-implemented neural network, that represent changes in a network graph across time steps, with a temporal factor for each time step depending on a temporal factor for a previous time step. An invariant factor is inferred that represents information about the network graph that does not change across the time steps. The temporal factors and the invariant factor are combined into a combined temporal-invariant representation. It is determined that an unlabeled node is anomalous, based on the combined temporal-invariant representation. A security action is performed responsive to the determination that unlabeled node is anomalous.