-
公开(公告)号：US20220366047A1
公开(公告)日：2022-11-17
申请号：US17321280
申请日：2021-05-14
Applicant: Huawei Technologies Co., Ltd.
Inventor： Yang Zhou , Ronnie Salvador Giagone , Ibrahim AbuAlhaol
Abstract: Methods and systems for detecting whether an executable file comprises malware are disclosed. The methods and systems rely on various feature extraction and feature representation processes to allow patterns associated with Portable Executable (PE) files to be analyzed in an improved representation space. In one example, six different feature sets are extracted from a PE file and represented in six different feature spaces, before being input into a multivariate ensemble deep neural network-based model.
-
公开(公告)号：US11574054B2
公开(公告)日：2023-02-07
申请号：US17093882
申请日：2020-11-10
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor： Ibrahim Yakub Abu Alhaol , Ronnie Salvador Giagone , Yang Zhou
Abstract: The disclosed systems and methods are directed to a method for malicious software detection comprising: recognizing and extracting an EP section in an unrecognized PE file, collecting bytes in the EP section of the unrecognized PE file, converting the bytes to an array of integers, generating one or more n-grams from the array of integers, converting the one or more n-grams into b-MinHash, converting the bytes in an EP function included in the EP section to an array of assembly-based mnemonics; generating one or more n-grams from the array of assembly-based mnemonics and converting the one or more n-grams from the array of assembly-based mnemonics into a-MinHash, generating a similarity matrices, converting, the similarity matrices into a lower dimensionality code representation, and classifying the code as a PE benign or a malware file.
-
公开(公告)号：US12093388B2
公开(公告)日：2024-09-17
申请号：US17321280
申请日：2021-05-14
Applicant: Huawei Technologies Co., Ltd.
Inventor： Yang Zhou , Ronnie Salvador Giagone , Ibrahim AbuAlhaol
CPC classification number: G06F21/566 , G06F21/565 , G06N3/02 , G06F2221/034
Abstract: Methods and systems for detecting whether an executable file comprises malware are disclosed. The methods and systems rely on various feature extraction and feature representation processes to allow patterns associated with Portable Executable (PE) files to be analyzed in an improved representation space. In one example, six different feature sets are extracted from a PE file and represented in six different feature spaces, before being input into a multivariate ensemble deep neural network-based model.
-
Patent Agency Ranking
公开(公告)号：US12034627B2
公开(公告)日：2024-07-09
申请号：US18059674
申请日：2022-11-29
Applicant: Huawei Technologies Co., Ltd.
Inventor： Yinxi Zhang , Yang Zhou , Bin Yu , Jiayuan Yang
IPC: H04L43/50 , H04L41/14 , H04L43/0811
CPC classification number: H04L43/50 , H04L41/145 , H04L43/0811
Abstract: A method includes: obtaining a service intent, where the service intent is used to indicate to perform a first network operation on the target network; obtaining a mirror simulation network corresponding to the target network; determining verification content, where the verification content is used to perform simulation verification on a running state of the mirror simulation network; performing the first network operation on the mirror simulation network based on the service intent; and performing, after the first network operation is performed on the mirror simulation network, simulation verification on the mirror simulation network based on the verification content, to obtain a first verification result, where the first verification result is used to evaluate impact of the first network operation on the target network.
-
公开(公告)号：US20230284319A1
公开(公告)日：2023-09-07
申请号：US18006513
申请日：2021-07-26
Applicant: Huawei Technologies Co., Ltd.
Inventor： Hao Luo , Yang Zhou , Liang Ning , Qiuyu Wu , Jin Liu
IPC: H04W76/20 , H04B17/318
CPC classification number: H04W76/20 , H04B17/328
Abstract: The method includes: a first electronic device detects signal strength existing when the first electronic device communicates with a second electronic device, and determines whether the signal strength is less than a preset value; when the signal strength is less than the preset value, the first electronic device determines a current service state of the second electronic device, and determines, based on the current service state, working modes that respectively correspond to the first electronic device and the second electronic device and that are suitable for the current service state; and the first electronic device switches a working mode to the determined working mode that corresponds to the first electronic device and that is suitable for the current service state, and sends an instruction to indicate the second electronic device to switch a working mode to the determined working mode that corresponds to the second electronic device.
-
公开(公告)号：US20240030205A1
公开(公告)日：2024-01-25
申请号：US18044434
申请日：2021-09-02
Applicant: Huawei Technologies Co., Ltd.
Inventor： Haohui Long , Yang Zhou
IPC: H01L25/16 , H01L25/075 , H01L21/683 , H01L23/538 , H01L33/62
CPC classification number: H01L25/167 , H01L25/0753 , H01L21/6835 , H01L23/5387 , H01L33/62 , H01L2221/68354 , H01L2221/68368 , H01L2933/0066
Abstract: A display screen includes a redistribution layer, a plurality of light emitting units, and a plurality of driver chips. The redistribution layer includes a flexible dielectric layer and a metal interconnection structure disposed in the flexible dielectric layer. The light emitting unit includes at least one light emitting chip. The light emitting diode is disposed on the redistribution layer. A pad of the light emitting chip is bonded to the metal interconnection structure. The plurality of driver chips are disposed on the redistribution layer. A pad of the driver chip is bonded to the metal interconnection structure. One driver chip is electrically connected to light emitting chips in the same light emitting unit by using metal interconnection structure, and the driver chip is configured to drive the light emitting chip to emit light.
-
公开(公告)号：US20230087249A1
公开(公告)日：2023-03-23
申请号：US18059674
申请日：2022-11-29
Applicant: Huawei Technologies Co., Ltd.
Inventor： Yinxi Zhang , Yang Zhou , Bin Yu , Jiayuan Yang
IPC: H04L43/50 , H04L41/14 , H04L43/0811
Abstract: A method includes: obtaining a service intent, where the service intent is used to indicate to perform a first network operation on the target network; obtaining a mirror simulation network corresponding to the target network; determining verification content, where the verification content is used to perform simulation verification on a running state of the mirror simulation network; performing the first network operation on the mirror simulation network based on the service intent; and performing, after the first network operation is performed on the mirror simulation network, simulation verification on the mirror simulation network based on the verification content, to obtain a first verification result, where the first verification result is used to evaluate impact of the first network operation on the target network.
-
8.发明授权公开(公告)号：US11574187B2
公开(公告)日：2023-02-07
申请号：US16809270
申请日：2020-03-04
Inventor： Bailan Feng , Chunfeng Yao , Kaiqi Huang , Zhang Zhang , Yang Zhou
IPC: G06N3/08 , G06F9/54 , G06K9/62 , G08G1/005 , G06V30/262
Abstract: A method for pedestrian attribute identification and positioning is provided. The method includes: performing feature extraction on a to-be-detected image at a plurality of different abstraction degrees, to obtain a plurality of first feature maps of a pedestrian attribute; performing convolution on the plurality of first feature maps, to obtain a plurality of second feature maps; mapping each second feature map to a plurality of areas (bins) that overlap each other, and performing max pooling on each bin, to obtain a plurality of high-dimensional feature vectors, where the plurality of bins that overlap each other evenly cover each second feature map; processing the plurality of high-dimensional feature vectors into a low-dimensional vector, to obtain an identification result of the pedestrian attribute; and further obtaining a positioning result of the pedestrian attribute based on the plurality of second feature maps and the plurality of high-dimensional feature vectors.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.016 seconds)
