Neural Network Application Name Classification for GPS Spoofing Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Ride-hailing organizations face challenges in identifying and preventing GPS spoofing applications used by drivers, which leads to mistrust and operational inefficiencies, as existing methods rely on manual review and are time-consuming and prone to evasion due to constantly changing patterns in application names.
Innovation Solution
A machine learning-based system that generates a numeric representation of application names using a neural network to predict whether an application is a location-spoofing application, leveraging a variable derived from a list of known applications to classify and optimize predictions over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual review methods are used to identify GPS spoofing applications, then the process is simple to implement, but it is time-consuming and prone to evasion due to constantly changing patterns
Solution Approach 1:
The patent replaces manual review processes with an automated machine learning system that uses neural networks to analyze application names and determine spoofing likelihood. This substitution enables rapid processing of applications while maintaining high detection accuracy through learned patterns, directly resolving the contradiction between identification speed and detection accuracy.
Solution Approach 2:
The system transforms application names into numeric representations and uses probability scores to quantify spoofing likelihood. By changing the parameters from qualitative manual assessment to quantitative numeric analysis, the system achieves both high speed automation and reliable detection through consistent mathematical evaluation.
2Reliability
If traditional detection methods are used, then the system complexity is low, but the ability to detect evolving spoofing patterns is insufficient
Solution Approach 1:
The patent replaces simple rule-based detection with a neural network-based machine learning system. This substitution provides superior pattern detection capability by learning from training data, while the modular architecture keeps system complexity manageable through standardized components.
Solution Approach 2:
The system performs self-improvement through continuous learning from new data. The neural network automatically updates its patterns and parameters based on training, enabling it to detect evolving spoofing techniques without increasing operational complexity for users.
3Measurement precision
If a comprehensive analysis of all applications is performed, then detection accuracy improves, but processing time increases
Solution Approach 1:
The system performs comprehensive analysis only during the training phase, then uses the learned model for rapid inference on new applications. This approach achieves high classification accuracy through thorough initial analysis while minimizing processing time for actual detection through efficient pattern matching.
Solution Approach 2:
The system performs preliminary training and pattern learning before actual detection operations. By pre-processing and learning from training data in advance, the system achieves high detection accuracy during operation without incurring processing time delays, as the heavy analysis work is completed beforehand.
Data Source
AI summary
The present disclosure provides an apparatus and a method for determining a location-spoofing application, the method comprising: generating a numeric representation of an application name of an application used for generating a geolocation position signal of a user using a variable derived from a list of application names relating to a plurality of other applications capable of generating a geolocation position signal of a user; and determining a prediction on whether the application is a location-spoofing application based on a scale of the generated numeric representation of the application name.