Device-Specific Lean Classifier Models for Mobile Security
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing solutions for mobile computing devices fail to efficiently identify and address the complex factors contributing to performance degradation over time, as they require computationally-intensive processes, are limited to detecting known viruses, and do not account for device-specific features or dynamic states, leading to significant resource consumption and user experience degradation.
Innovation Solution
A system where servers and mobile devices collaborate to generate device-specific lean classifier models based on capabilities and states, allowing the mobile device to focus on relevant features for behavior analysis without significant performance impact, using lean classifier models that can be updated dynamically to reflect changes in device functionality and state.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If computationally-intensive processes are used to identify performance degradation factors, then detection accuracy is improved, but resource consumption increases
Solution Approach 1:
The system segments the classifier model into device-specific components and state-specific components. The server generates and provides pre-computed device-specific classifier models tailored to each device's capabilities, while the mobile device computes state-specific classifications locally based on current device states. This segmentation allows complex analysis to be distributed, reducing real-time computational burden on the mobile device while maintaining high detection accuracy through specialized pre-computed models.
2Device complexity
If generic classifier models are used without device-specific customization, then model complexity is reduced, but detection precision deteriorates
Solution Approach 1:
The system applies local quality by creating device-specific classifier models that are customized to each mobile device's unique capabilities, hardware configuration, and operational characteristics. The server generates these specialized models based on device-specific information, ensuring that each device receives a model optimized for its particular architecture and behavior patterns, thereby achieving high detection precision without requiring all devices to handle full model complexity.
3Reliability
If comprehensive behavior analysis covering all device features is performed, then detection coverage is improved, but processing time increases
Solution Approach 1:
The system performs preliminary action by pre-computing device-specific classifier models on the server before they are deployed to mobile devices. These pre-computed models encapsulate comprehensive behavior analysis for the specific device type, so that during actual operation, the mobile device only needs to perform lightweight state-specific classification using the pre-prepared model, significantly reducing processing time while maintaining comprehensive detection coverage.
4Adaptability or versatility
If device-specific classifier models are generated and maintained, then adaptability to different devices is improved, but system complexity increases
Solution Approach 1:
The system introduces an intermediary server that acts as a mediator between model generation and deployment. The server handles the complex tasks of generating, storing, and managing device-specific classifier models, while mobile devices simply request and use these pre-computed models. This intermediary architecture enables high adaptability to different devices without requiring each device to independently manage the complexity of model generation and maintenance.
Data Source
AI summary
The various aspects provide a system and methods implemented on the system for generating a behavior model on a server that includes features specific to a mobile computing device and the device's current state/configuration. In the various aspects, the mobile computing device may send information identifying itself, its features, and its current state to the server. In response, the server may generate a device-specific lean classifier model for the mobile computing device based on the device's information and state and may send the device-specific lean classifier model to the device for use in detecting malicious behavior. The various aspects may enhance overall security and performance on the mobile computing device by leveraging the superior computing power and resources of the server to generate a device-specific lean classifier model that enables the device to monitor features that are actually present on the device for malicious behavior.