专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2021178011A1 A NEURAL NETWORK ARCHITECTURE FOR SMALL LIDAR PROCESSING NETWORKS FOR SLOPE ESTIMATION AND GROUND PLANE SEGMENTATION 审中-公开
公开(公告)号：WO2021178011A1
公开(公告)日：2021-09-10
申请号：PCT/US2020/060924
申请日：2020-11-17
申请人： HRL LABORATORIES, LLC
发明人： SERRANO, Christopher , WARREN, Michael, A. , NOGIN, Aleksey
IPC分类号： G06N5/00 , G06N3/10 , G06N3/04 , G06N3/08 , G01S7/48 , G01S17/89 , G01S17/931
摘要： Described is a system for training a neural network for estimating surface normals for use in operating an autonomous platform. The system uses a parallelizable k-nearest neighbor sorting algorithm to provide a patch of points, sampled from the point cloud data, as input to the neural network model. The points are transformed from Euclidean coordinates in a Euclidean space to spherical coordinates. A polar angle of a surface normal of the point cloud data is estimated in the spherical coordinates. The trained neural network model is utilized on the autonomous platform, and the estimate of the polar angle of the surface normal is used to guide operation of the autonomous platform within the environment.

2. 发明申请

WO2020033033A1 ANONYMOUS ALLOCATION AND MAJORITY VOTING IN A COMPROMISED ENVIRONMENT 审中-公开
公开(公告)号：WO2020033033A1
公开(公告)日：2020-02-13
申请号：PCT/US2019/035854
申请日：2019-06-06
申请人： HRL LABORATORIES, LLC
发明人： BARON, Joshua, W. , EL DEFRAWY, Karim , NOGIN, Aleksey , CHO, Chongwon
IPC分类号： H04L9/06
摘要： Described is a system for anonymous job allocation and majority voting in a cloud computing environment. The system broadcasts a job to physical nodes, each of the physical nodes having a control operations plane (COP) node and one or more service nodes associated with the COP node. A set of redundant job assignments is distributed to individual COP nodes pursuant to a private job assignment schedule, such that each individual COP node is only aware of its own assignment and corresponding job. The service nodes execute the job assigned to the COP nodes such that the service nodes each complete a task associated with the job and forward an individual result to their associated COP node. A privacy-preserving result checking protocol is performed amongst the COP nodes such that secret shares of a majority result are obtained and the majority result is provided to a client.

3. 发明申请

WO2017075546A1 SYSTEM AND METHOD FOR MAINTAINING SECURITY TAGS AND REFERENCE COUNTS FOR OBJECTS IN COMPUTER MEMORY 审中-公开
标题翻译：用于维护计算机存储器中的对象的安全标签和参考计数的系统和方法
公开(公告)号：WO2017075546A1
公开(公告)日：2017-05-04
申请号：PCT/US2016/059597
申请日：2016-10-28
申请人： HRL LABORATORIES, LLC
发明人： KUAN, George , NOGIN, Aleksey
IPC分类号： G06F21/71 , G06F21/12 , G06F21/55
CPC分类号： G06F21/566 , G06F17/30002 , G06F21/54 , G06F21/577 , G06F2221/034
摘要： Described is a system and method for monitoring and enforcing information Sow security in software systems. The system maintains security tags and reference counts for objects in computer memory. When an object or a portion of an object in the computer memory Is being modified, the system arbitrarily performs operations of updating a security tag for the object being modified; updating reference counts for all objects that the portion of the object in the computer memory being modified pointed to immediately prior to modification; and updating reference counts for all objects that the portion of the object in the computer memory being modified points to immediately after the modification. Subsequently, the system examines the security tags and If the examination reveals a potential information flow security violation, a corrective action is performed.
摘要翻译：描述了用于在软件系统中监视和实施信息Sow安全性的系统和方法。系统为计算机内存中的对象维护安全标签和引用计数。当计算机存储器中的对象或部分对象被修改时，系统任意执行更新被修改对象的安全标签的操作; 更新所修改的计算机存储器中的对象部分在修改之前指向的所有对象的引用计数; 以及更新所修改的计算机存储器中的对象部分在修改后立即指向的所有对象的引用计数。随后，系统检查安全标签，如果检查发现潜在的信息流安全违规，则执行纠正措施。

4. 发明申请

WO2021178009A1 METHOD FOR PROVING OR IDENTIFYING COUNTER-EXAMPLES IN NEURAL NETWORKS SYSTEMS THAT PROCESS POINT CLOUD DATA 审中-公开
公开(公告)号：WO2021178009A1
公开(公告)日：2021-09-10
申请号：PCT/US2020/056943
申请日：2020-10-22
申请人： HRL LABORATORIES, LLC
发明人： WARREN, Michael A. , SERRANO, Christopher , NOGIN, Aleksey
IPC分类号： G06N5/00 , G06N3/10 , G06N3/04 , G06N3/08
摘要： Described is a system for proving correctness properties of a neural network for providing estimates for point cloud data. The system receives as input a description of a neural network for generating estimates from a set of point cloud data. The description of the neural network is parsed to obtain a symbolic representation. Based on a combination of the symbolic representation and a set of analysis parameters, the system generates an analysis output indicating whether the neural network satisfies a correctness property in generating the estimates from the set of point cloud data. The analysis output is a mathematical proof artifact proving that the set of analysis parameters is satisfied, a list of one or more point clouds for which the set of analysis parameters is violated, or a report that progress could not be made by the analysis.

5. 发明申请

WO2020033048A1 SYSTEM AND METHOD FOR CONSENSUS ORDERING OF BROADCAST MESSAGES 审中-公开
公开(公告)号：WO2020033048A1
公开(公告)日：2020-02-13
申请号：PCT/US2019/038724
申请日：2019-06-24
申请人： HRL LABORATORIES, LLC
发明人： NOGIN, Aleksey , LAMPKINS, Joshua, D.
IPC分类号： H04L12/18 , H04L29/06
摘要： The system is directed to a plurality of nodes in a network and a process by which the nodes reach a consensus ordering of broadcast messages. For example, one or more nodes proceed by agreeing on an order of two or more broadcast message derived events A and B. If a node sees event A longer than a time period (T6) before seeing event B, then the node outputs "A consensus-before B" as a consensus broadcast ordering. If the node sees the event A and not the event B after waiting at least T6, then the node outputs "A consensus-before B" as a consensus broadcast ordering. However, if the node sees both events A and event B within T6, then the node broadcasts a request for a vote on message ordering, executes a consensus broadcast reception protocol for the votes, and makes an ordering decision based on the votes received.

6. 发明申请

WO2019055116A1 HIGH-ASSURANCE NETWORK GATEWAY GENERATORS 审中-公开
公开(公告)号：WO2019055116A1
公开(公告)日：2019-03-21
申请号：PCT/US2018/041902
申请日：2018-07-12
申请人： HRL LABORATORIES, LLC
发明人： NOGIN, Aleksey , WARREN, Michael, A. , HOLLAND, Gavin, D.
IPC分类号： G06F9/30
摘要： Described is a high-assurance network gateway generator that generates and encodes network gateway code on a computer readable medium. In operation, the network gateway generator receives input artifacts, which are translated into corresponding formats as translated data. The translated data is distributed to an OS code generator, a glue code generator, and a communications code generator. The OS code generator then generates OS code based on the translated data. The communications code generator proceeds to generate deserialization and filtering code based on the translated data. Further, a glue code generator generates glue code based on the OS code and translated data. An executable network gateway code is then generated by combining the glue code, deserialization code, and filtering code. Finally, the executable network gateway code is then encoded on a computer readable medium.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式