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. 发明公开

EP2941741A2 METHODS AND SYSTEMS OF USING BOOSTED DECISION STUMPS AND JOINT FEATURE SELECTION AND CULLING ALGORITHMS FOR THE EFFICIENT CLASSIFICATION OF MOBILE DEVICE BEHAVIORS 审中-公开
标题翻译：方法和系统决策方法，连接功能选择增加用途和移动设备做法的高效分类排序算法
公开(公告)号：EP2941741A2
公开(公告)日：2015-11-11
申请号：EP13829028.3
申请日：2013-12-30
申请人： Qualcomm Incorporated
发明人： FAWAZ, Kassem , SRIDHARA, Vinay , GUPTA, Rajarshi
IPC分类号： G06N5/04
CPC分类号： G06N5/043 , G06N5/025
摘要： Methods and systems for classifying mobile device behavior include configuring a server use a large corpus of mobile device behaviors to generate a full classifier model that includes a finite state machine suitable for conversion into boosted decision stumps and/or which describes all or many of the features relevant to determining whether a mobile device behavior is benign or contributing to the mobile device's degradation over time. A mobile device may receive the full classifier model and use the model to generate a full set of boosted decision stumps from which a more focused or lean classifier model is generated by culling the full set to a subset suitable for efficiently determining whether mobile device behavior are benign. Boosted decision stumps may be culled by selecting all boosted decision stumps that depend upon a limited set of test conditions.
摘要翻译：方法和系统分类移动装置行为包括配置服务器使用移动设备的行为的大语料库，以生成完整的分类模型确实包括适合改装的有限状态机进入提振决定树桩和/或它描述全部或许多功能有关确定性采矿无论移动装置行为是良性还是随着时间的推移有利于移动设备的退化。移动设备可以接收完整分类器模型和使用该模型来生成从由剔除全套到适于有效确定性采矿无论移动设备的行为是一个子集产生的一个更加集中或贫分类器模型全套升压决定树桩良性的。提高决策树桩可以通过选择所有提高决策的树桩也依赖于一组有限的测试条件被剔除。

2. 发明公开

EP3074910A1 PRE-IDENTIFYING PROBABLE MALICIOUS ROOTKIT BEHAVIOR USING BEHAVIORAL CONTRACTS 审中-公开
标题翻译： ROOTKIT行为的可能恶意使用行为的协议预先判别
公开(公告)号：EP3074910A1
公开(公告)日：2016-10-05
申请号：EP14812039.7
申请日：2014-11-13
申请人： Qualcomm Incorporated
发明人： FIALA, David , CHRISTODORESCU, Mihai , SRIDHARA, Vinay , GUPTA, Rajarshi , FAWAZ, Kassem
IPC分类号： G06F21/56
CPC分类号： G06F21/56 , G06F21/566
摘要： The various aspects provide for a computing device and methods implemented by the device to ensure that an application executing on the device and seeking root access will not cause malicious behavior while after receiving root access. Before giving the application root access, the computing device may identify operations the application intends to execute while having root access, determine whether executing the operations will cause malicious behavior by simulating execution of the operations, and pre-approve those operations after determining that executing those operations will not result in malicious behavior. Further, after giving the application root access, the computing device may only allow the application to perform pre-approved operations by quickly checking the application's pending operations against the pre-approved operations before allowing the application to perform those operations. Thus, the various aspects may ensure that an application receives root access without compromising the performance or security integrity of the computing device.

3. 发明公开

EP3335160A1 USING NORMALIZED CONFIDENCE VALUES FOR CLASSIFYING MOBILE DEVICE BEHAVIORS 审中-公开
公开(公告)号：EP3335160A1
公开(公告)日：2018-06-20
申请号：EP16742116.3
申请日：2016-07-08
申请人： Qualcomm Incorporated
发明人： FAWAZ, Kassem , SRIDHARA, Vinay , GUPTA, Rajarshi , CHEN, Yin
IPC分类号： G06N99/00
CPC分类号： G06N99/005 , G06F21/552 , G06N5/025 , G06N5/043
摘要： Methods and systems for classifying mobile device behavior include generating a full classifier model that includes a finite state machine suitable for conversion into boosted decision stumps and/or which describes all or many of the features relevant to determining whether a mobile device behavior is benign or contributing to the mobile device's degradation over time. A mobile device may receive the full classifier model along with sigmoid parameters and use the model to generate a full set of boosted decision stumps from which a more focused or lean classifier model is generated by culling the full set to a subset suitable for efficiently determining whether mobile device behavior are benign. Results of applying the focused or lean classifier model may be normalized using a sigmoid function, with the resulting normalized result used to determine whether the behavior is benign or non-benign.

4. 发明公开

EP2941740A2 METHODS AND SYSTEMS OF DYNAMICALLY GENERATING AND USING DEVICE-SPECIFIC AND DEVICE-STATE-SPECIFIC CLASSIFIER MODELS FOR THE EFFICIENT CLASSIFICATION OF MOBILE DEVICE BEHAVIORS 审中-公开
标题翻译：方法和系统动态生产和具体KLASSIFIKATORMODELLE专用型设备和设备状态的的移动设备做法的高效使用分类
公开(公告)号：EP2941740A2
公开(公告)日：2015-11-11
申请号：EP13824278.9
申请日：2013-12-30
申请人： Qualcomm Incorporated
发明人： SRIDHARA, Vinay , GUPTA, Rajarshi , FAWAZ, Kassem
IPC分类号： G06N5/04
CPC分类号： H04B17/391 , G06N5/003 , G06N5/043 , G06N99/005
摘要： The various aspects provide a mobile device and methods implemented on the mobile device for modifying behavior models to account for device-specific or device-state-specific features. In the various aspects, a behavior analyzer module may leverage a full feature set of behavior models (i.e. a large classifier model) received from a network server to create lean classifier models for use in monitoring for malicious behavior on the mobile device, and the behavior analyzer module may dynamically modify these lean classifier models to include features specific to the mobile device and/or the mobile device's current configuration. Thus, the various aspects may enhance overall security for a particular mobile device by taking the mobile device and its current configuration into account and may improve overall performance by monitoring only features that are relevant to the mobile device.
摘要翻译：各种方面提供实现在移动设备上修改行为模型考虑到设备特定或设备状态的特定功能的移动设备和方法。在各个方面，行为分析模块可以利用行为模型的完整功能集（即一个大的分类模型）从网络服务器创建的监控移动设备上的恶意行为利用精益分类模型和行为收到分析器模块可动态地修改本文贫分类模型，以包括特定于移动设备和/或所述移动设备的当前配置的特征。因此，各方面可以加强对特定移动设备整体安全通过采取移动设备及其当前配置的考虑，可能仅特点做监测提高整体性能相关的移动设备。

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