Methods and systems of dynamically generating and using device-specific and device-state-specific classifier models for the efficient classification of mobile device behaviors
First Claim
1. A method of generating and using data models in a mobile device, comprising:
- receiving, in a processor of the mobile device from a server computing device, a full classifier model, the received full classifier model including a plurality of decision nodes, each decision node in the plurality of decision nodes including a test condition and a weight value;
collecting mobile device-specific information in the mobile device;
identifying combinations of features that require monitoring and analysis in the mobile device, and determining a relative importance of each of the identified feature combinations, based on the collected mobile device-specific information;
culling, via the processor of the mobile device, the received full classifier model to generate a lean classifier model that includes a subset of the plurality of decision nodes included in the received full classifier model, the culling comprising;
identifying decision nodes included in the received full classifier model that include test conditions relevant to evaluating the identified feature combinations;
prioritizing the identified decision nodes based on determined relative importance of the identified feature combinations; and
generating the lean classifier model to include only the identified decision nodes, ordered in accordance with their priority;
generating a behavior vector that characterizes a behavior of the mobile device; and
applying, by the processor of the mobile device, the generated behavior vector to the generated lean classifier model to classify the behavior of the mobile device.
1 Assignment
0 Petitions
Accused Products
Abstract
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.
196 Citations
30 Claims
-
1. A method of generating and using data models in a mobile device, comprising:
-
receiving, in a processor of the mobile device from a server computing device, a full classifier model, the received full classifier model including a plurality of decision nodes, each decision node in the plurality of decision nodes including a test condition and a weight value; collecting mobile device-specific information in the mobile device; identifying combinations of features that require monitoring and analysis in the mobile device, and determining a relative importance of each of the identified feature combinations, based on the collected mobile device-specific information; culling, via the processor of the mobile device, the received full classifier model to generate a lean classifier model that includes a subset of the plurality of decision nodes included in the received full classifier model, the culling comprising; identifying decision nodes included in the received full classifier model that include test conditions relevant to evaluating the identified feature combinations; prioritizing the identified decision nodes based on determined relative importance of the identified feature combinations; and generating the lean classifier model to include only the identified decision nodes, ordered in accordance with their priority; generating a behavior vector that characterizes a behavior of the mobile device; and applying, by the processor of the mobile device, the generated behavior vector to the generated lean classifier model to classify the behavior of the mobile device. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A mobile device, comprising:
a processor configured with processor-executable instructions to perform operations comprising; receiving from a server computing device a full classifier model, the received full classifier model including a plurality of decision nodes, each decision node in the plurality of decision nodes including a test condition and a weight value; collecting mobile device-specific information in the mobile device; identifying combinations of features that require monitoring and analysis in the mobile device, and determining a relative importance of each of the identified feature combinations, based on the collected mobile device-specific information; culling the received full classifier model to generate a lean classifier model that includes a subset of the plurality of decision nodes included in the received full classifier model, the culling comprising; identifying decision nodes included in the received full classifier model that include test conditions relevant to evaluating the identified feature combinations; prioritizing the identified decision nodes based on the determined relative importance of the identified feature combinations; and generating the lean classifier model to include only the identified decision nodes, ordered in accordance with their priority; generating a behavior vector that characterizes a behavior of the mobile device; and applying the generated behavior vector to the generated lean classifier model in the mobile device to classify the behavior of the mobile device. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 18)
-
19. A non-transitory computer readable storage medium having stored thereon processor-executable software instructions configured to cause a processor of a mobile device to perform operations comprising:
-
receiving from a server computing device a full classifier model, the received full classifier model including a plurality of decision nodes, each decision node in the plurality of decision nodes including a test condition and a weight value; collecting mobile device-specific information in the mobile device; identifying combinations of features that require monitoring and analysis in the mobile device, and determining a relative importance of each of the identified feature combinations, based on the collected mobile device-specific information; culling the received full classifier model to generate a lean classifier model that includes a subset of the plurality of decision nodes included in the received full classifier model, the culling comprises; identifying decision nodes included in the received full classifier model that include test conditions relevant to evaluating the identified feature combinations; prioritizing the identified decision nodes based on the determined relative importance of the identified feature combinations; and generating the lean classifier model to include only the identified decision nodes, ordered in accordance with their priority; generating a behavior vector that characterizes a behavior of the mobile device; and applying the generated behavior vector to the generated lean classifier model in the mobile device to classify the behavior of the mobile device. - View Dependent Claims (20, 21, 22, 23, 24, 25, 26, 27)
-
-
28. A mobile device, comprising:
-
means for receiving from a server computing device a full classifier model, the received full classifier model including a plurality of decision nodes, each decision node in the plurality of decision nodes including a test condition and a weight value; means for collecting mobile device-specific information in the mobile device; means for identifying combinations of features that require monitoring and analysis in the mobile device, and determining a relative importance of each of the identified feature combinations, based on the collected mobile device-specific information; means for culling, via the processor of the mobile device, the received full classifier model to generate a lean classifier model that includes a subset of the plurality of decision nodes included in the received full classifier model, the means for culling comprising; means for identifying decision nodes included in the received full classifier model that include test conditions relevant to evaluating the identified feature combinations; means for prioritizing the identified decision nodes based on the determined relative importance of the identified feature combinations; and means for generating the lean classifier model to include only the identified decision nodes, ordered in accordance with their priority; means for generating a behavior vector that characterizes a behavior of the mobile device; and means for applying the generated behavior vector to the generated lean classifier model to classify the behavior of the mobile device. - View Dependent Claims (29, 30)
-
Specification