公开(公告)号：US20170083827A1

公开(公告)日：2017-03-23

申请号：US14862408

申请日：2015-09-23

Applicant: QUALCOMM Incorporated

Inventor： Behnam Robatmili ,  Matthew Leslie Badin ,  Dario Suárez Gracia ,  Gheorghe Calin Cascaval ,  Nayeem Islam

IPC: G06N99/00

CPC classification number: G06N20/00 ,  G06F15/8092

Abstract: Embodiments include computing devices, apparatus, and methods implemented by the apparatus for accelerating machine learning on a computing device. Raw data may be received in the computing device from a raw data source device. The apparatus may identify key features as two dimensional matrices of the raw data such that the key features are mutually exclusive from each other. The key features may be translated into key feature vectors. The computing device may generate a feature vector from at least one of the key feature vectors. The computing device may receive a first partial output resulting from an execution of a basic linear algebra subprogram (BLAS) operation using the feature vector and a weight factor. The first partial output may be combined with a plurality of partial outputs to produce an output matrix. Receiving the raw data on the computing device may include receiving streaming raw data.

公开(公告)号：US09292685B2

公开(公告)日：2016-03-22

申请号：US13747115

申请日：2013-01-22

Applicant: QUALCOMM Incorporated

Inventor： Rajarshi Gupta ,  Nayeem Islam ,  Saumitra Das

IPC: G06F11/00 ,  G06F21/55 ,  G06F21/56 ,  G06F11/14 ,  G06F11/30 ,  H04W52/02 ,  H04W24/08 ,  G06F11/34 ,  H04W12/12 ,  H04W88/02 ,  H04L29/06

CPC classification number: G06F21/552 ,  G06F11/1433 ,  G06F11/1458 ,  G06F11/3006 ,  G06F11/3082 ,  G06F11/3409 ,  G06F11/3466 ,  G06F11/3476 ,  G06F21/554 ,  G06F21/56 ,  G06F2201/86 ,  G06N99/005 ,  H04L63/1433 ,  H04W12/12 ,  H04W24/08 ,  H04W52/0251 ,  H04W52/0258 ,  H04W88/02 ,  Y02D10/34 ,  Y02D70/1242 ,  Y02D70/1262 ,  Y02D70/142 ,  Y02D70/144 ,  Y02D70/146 ,  Y02D70/164 ,  Y02D70/166 ,  Y02D70/21 ,  Y02D70/22

Abstract: Aspect methods, systems and devices may be configured to create/capture checkpoints without significantly impacting the performance, power consumption, or responsiveness of the mobile device. An observer module of the mobile device may instrument or coordinate various application programming interfaces (APIs) at various levels of the mobile device system and constantly monitor the mobile device (via a low power process, background processes, etc.) to identify the normal operation patterns of the mobile device and/or to identify behaviors that are not consistent with previously computed normal operation patterns. The mobile device may store mobile device state information in a memory as a stored checkpoint when it determines that the mobile device behaviors are consistent with normal operation patterns, and upload a previously stored checkpoint to a backup storage system when it determines that the mobile device behaviors are not consistent with normal operation patterns.

Abstract translation: 方面方法，系统和设备可以被配置为创建/捕获检查点，而不会显着影响移动设备的性能，功耗或响应性。 移动设备的观察者模块可以在移动设备系统的各个级别对各种应用编程接口（API）进行仪器或协调，并且不断监视移动设备（经由低功率过程，后台进程等）来识别正常操作 移动设备的模式和/或识别与先前计算的正常操作模式不一致的行为。 当确定移动设备的行为与正常操作模式一致时，移动设备可以将存储器中的移动设备状态信息存储在存储器中，并且当它确定移动设备行为时将先前存储的检查点上传到备份存储系统 与正常的操作模式不一致。

公开(公告)号：US10101196B2

公开(公告)日：2018-10-16

申请号：US15046390

申请日：2016-02-17

Applicant: QUALCOMM Incorporated

Inventor： Ayman Naguib ,  Nayeem Islam

IPC: G01S5/00 ,  G01H3/08 ,  G01S5/18 ,  G01V1/00 ,  G08B13/00

Abstract: Apparatuses and methods are described herein for identifying a Unmanned Aerial Vehicle (UAV), including, but not limited to, determining a first maneuver type, determining a first acoustic signature of sound captured by a plurality of audio sensors while the UAV performs the first maneuver type, determining a second acoustic signature of sound captured by the plurality of audio sensors while the UAV performs a second maneuver type different from the first maneuver type, determining an acoustic signature delta based on the first acoustic signature and the second acoustic signature, and determining an identity of the UAV based on the acoustic signature delta.

公开(公告)号：US20180131705A1

公开(公告)日：2018-05-10

申请号：US15428944

申请日：2017-02-09

Applicant: QUALCOMM Incorporated

Inventor： Ramin Samadani ,  Yin Chen ,  Keen Yuun Sung ,  Nayeem Islam

IPC: H04L29/06 ,  H04L12/26 ,  G06N99/00

CPC classification number: H04L63/1425 ,  G06N20/00 ,  H04L43/026 ,  H04L43/0876 ,  H04L47/2475 ,  H04L47/35 ,  H04L63/0236 ,  H04L63/0245 ,  H04L63/1408

Abstract: Embodiments provide methods of protecting computing devices from malicious activity. A processor of a network device may receive a first network traffic flow of a monitoring computing device and a malicious activity tag identifying a malicious behavior of the first network traffic flow. The processor may determine a characteristic of the first network traffic flow based at least in part on information in the first network traffic flow and the malicious activity tag. The processor may receive a second network traffic flow from a non-monitoring computing device, and may associate the malicious activity tag and the second network traffic flow based on a characteristic of the second network traffic flow based at least in part on information in the second network traffic flow and the characteristic of the first network traffic flow.

公开(公告)号：US20180124080A1

公开(公告)日：2018-05-03

申请号：US15455774

申请日：2017-03-10

Applicant: QUALCOMM Incorporated

Inventor： Mihai Christodorescu ,  Nayeem Islam ,  Arun Raman ,  Shuhua Ge

IPC: H04L29/06

CPC classification number: H04L63/1425 ,  G06F21/552 ,  G06F21/554 ,  G06F21/577 ,  G06F21/85 ,  H04L63/1433

Abstract: Various embodiments include methods of protecting a computing device within a network from malware or other non-benign behaviors. A computing device may monitor inputs and outputs to a server, derive a functional specification from the monitored inputs and outputs, and use the functional specification for anomaly detection. Use of the derived functional specification for anomaly detection may include determining whether a behavior, activity, web application, process or software application program is non-benign. The computing device may be the server, and the functional specification may be used to determine whether the server is under attack. In some embodiments, the computing device may constrain the functional specification with a generic constraint, detect a new input-output pair, determine whether the detected input-output pair satisfies the constrained functional specification, and determine that the detected input-output pair is anomalous upon determining that the detected input-output pair (or request-response pair) satisfies the constrained functional specification.

公开(公告)号：US20180063179A1

公开(公告)日：2018-03-01

申请号：US15248178

申请日：2016-08-26

Applicant: QUALCOMM Incorporated

Inventor： Mastooreh Salajegheh ,  Sudha Anil Kumar Gathala ,  Saumitra Mohan Das ,  Nayeem Islam

IPC: H04L29/06 ,  G06F1/28

CPC classification number: H04L63/1433 ,  G06F1/28 ,  G06F21/564 ,  H04L63/1408

Abstract: Various embodiments include methods and a memory data collection processor for performing online memory data collection for memory forensics. Various embodiments may include determining whether an operating system executing in a computing device is trustworthy. In response to determining that the operating system is not trustworthy, the memory data collection processor may collect memory data directly from volatile memory. Otherwise, the operating system to collect memory data from volatile memory. Memory data may be collected at a variable memory data collection rate determined by the memory data collection processor. The memory data collection rate may depend upon whether an available power level of the computing device exceeds a threshold power level, whether an activity state of the processor of the computing device equals a sleep state whether a security risk exists on the computing device, and whether a volume of memory traffic in the volatile memory exceeds a threshold volume.

公开(公告)号：US20180054449A1

公开(公告)日：2018-02-22

申请号：US15240721

申请日：2016-08-18

Applicant: QUALCOMM Incorporated

Inventor： Sriram Nandha Premnath ,  Yin Chen ,  Saumitra Mohan Das ,  Nayeem Islam

IPC: H04L29/06 ,  G06F21/56

CPC classification number: H04L63/145 ,  G06F21/56 ,  G06F21/566 ,  G06F2221/033

Abstract: A network and its devices may be protected from non-benign behavior, malware, and cyber attacks by configuring a server computing device to work in conjunction with a multitude of client computing devices in the network. The server computing device may be configured to receive data that was collected from independent executions of different instances of the same software application on different client computing devices. The server computing device may combine the received data, and use the combined data to identify unexplored code space or potential code paths for evaluation. The server computing device may then exercise the software application through the identified unexplored code space or identified potential code paths in a client computing device emulator to generate analysis results, and use the generated analysis results to determine whether the software application is non-benign.

公开(公告)号：US20170134405A1

公开(公告)日：2017-05-11

申请号：US14935522

申请日：2015-11-09

Applicant: QUALCOMM Incorporated

Inventor： Seyed Ali Ahmadzadeh ,  Nayeem Islam ,  Mihai Christodorescu ,  Rajarshi Gupta ,  Saumitra Mohan Das

IPC: H04L29/06

CPC classification number: H04L63/1416 ,  G06F21/552 ,  G06F21/554 ,  G06F21/566 ,  G06F21/577 ,  G06F2221/033 ,  H04L63/1425 ,  H04L63/1433 ,  H04L63/1491

Abstract: Various embodiments include a honeypot system configured to trigger malicious activities by malicious applications using a behavioral analysis algorithm and dynamic resource provisioning. A method performed by a processor of a computing device, which may be a mobile computing device, may include determining whether or not a target application currently executing on the computing device is potentially malicious based, at least in part, on the analysis, predicting a triggering condition of the target application in response to determining the target application is potentially malicious, provisioning one or more resources based, at least in part, on the predicted triggering condition, monitoring activities of the target application corresponding to the provisioned one or more resources, and determining whether or not the target application is a malicious application based, at least in part, on the monitored activities. The resources may be device components (e.g., network interface(s), sensor(s), etc.) and/or data (e.g., files, etc.).

公开(公告)号：US20160274991A1

公开(公告)日：2016-09-22

申请号：US14660260

申请日：2015-03-17

Applicant: QUALCOMM Incorporated

Inventor： Mihai Christodorescu ,  Mastooreh Salajegheh ,  Rajarshi Gupta ,  Nayeem Islam

IPC: G06F11/34 ,  G06F11/30

CPC classification number: G06F11/3466 ,  G06F8/443 ,  G06F11/3003 ,  G06F11/302 ,  G06F11/3051 ,  G06F11/3495 ,  G06F11/3612 ,  G06F11/362 ,  G06F11/3624

Abstract: Various aspects provide systems and methods for optimizing hardware monitoring on a computing device. A computing device may receive a monitoring request to monitor a portion of code or data within a process executing on the computing device. The computing device may generate from the monitoring request a first monitoring configuration parameter for a first hardware monitoring component in the computing device and may identify a non-optimal event pattern that occurs while the first hardware monitoring component monitors the portion of code or data according to the first monitoring configuration parameter. The computing device may apply a transformation to the portion of code or data and reconfigure the first hardware monitoring component by modifying the first monitoring configuration parameter in response to the transformation of the portion of code or data.

Abstract translation: 各个方面提供用于优化计算设备上的硬件监视的系统和方法。 计算设备可以接收监视请求以监视在计算设备上执行的过程中的代码或数据的一部分。 所述计算设备可以从所述监视请求生成所述计算设备中的第一硬件监视组件的第一监视配置参数，并且可以识别当所述第一硬件监视组件根据所述第一硬件监视组件监视所述代码或数据的所述部分时发生的非最佳事件模式 第一个监控配置参数。 计算设备可以对代码或数据的一部分应用变换，并且通过响应于代码或数据的部分的变换来修改第一监视配置参数来重新配置第一硬件监视组件。

公开(公告)号：US20160171390A1

公开(公告)日：2016-06-16

申请号：US14680225

申请日：2015-04-07

Applicant: QUALCOMM Incorporated

Inventor： Faraz Mohammad Mirzaei ,  Vinay Sridhara ,  Nayeem Islam

IPC: G06N99/00

CPC classification number: G06N99/005 ,  G06F11/3438 ,  Y02D10/34

Abstract: Methods, devices, systems, and non-transitory process-readable storage media for a computing device to use machine learning to dynamically configure an application and/or complex algorithms associated with the application. An aspect method performed by a processor of the computing device may include operations for performing an application that calls a library function associated with a complex algorithm, obtaining signals indicating user responses to performance of the application, determining whether a user tolerates the performance of the application based on the obtained signals indicating the user responses, adjusting a configuration of the application to improve a subsequent performance of the application in response to determining the user does not tolerate the performance of the application, and storing data indicating the user responses to the performance of the application and other external variables for use in subsequent evaluations of user inputs.

Abstract translation: 用于计算设备的方法，设备，系统和非暂时过程可读存储介质，以使用机器学习来动态地配置与应用相关联的应用和/或复杂算法。 由计算设备的处理器执行的方面方法可以包括用于执行调用与复杂算法相关联的库函数的应用的操作，获得指示用户对应用的性能的响应的信号，确定用户是否容忍应用的性能 基于所获得的指示用户响应的信号，响应于确定用户来调整应用的配置以改善应用的后续性能不能容忍应用的性能，并且将表示用户响应的数据存储在 应用程序和其他外部变量用于后续评估用户输入。