Carrier-Aware Spam Message Detection Before Delivery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing spam detection systems for mobile devices rely solely on message content and user responses, making them vulnerable to bypass and ineffective in preventing phishing attacks, leading to potential identity theft and fraud.
Innovation Solution
A spam detection system utilizing carrier-determined information, such as geolocation, device identifiers, and transmission modes, combined with machine learning models, to classify text messages as spam or not spam before delivery, enabling real-time and batch inference for enhanced accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If spam detection systems rely solely on message content and user responses, then the system simplicity is maintained, but the detection accuracy and reliability are insufficient
Solution Approach 1:
The patent merges multiple information sources including carrier-determined information (device identifiers, geolocation, transmission modes), message content analysis, and user response data into a unified spam detection system. This combination of previously separate data sources enables more accurate spam detection while maintaining system manageability through integrated processing.
Solution Approach 2:
The spam detection system is designed to process and analyze multiple types of data universally - carrier-determined information, message content, user responses, and pattern recognition data - all through a single machine learning model that can handle diverse input formats and make comprehensive spam classification decisions.
2Measurement precision
If carrier-determined information is used for spam detection, then the measurement precision of spam identification is improved, but the difficulty of detecting and measuring increases
Solution Approach 1:
The patent introduces carrier-determined information as an intermediary data source that bridges the gap between network infrastructure and end-user devices. This intermediary layer provides objective, hard-to-fake data about device identity, location, and transmission characteristics that directly indicate spam sources without requiring complex analysis of message content or user behavior.
3Productivity
If real-time and batch inference are implemented, then the productivity of spam filtering is improved, but the use of energy increases
Solution Approach 1:
The patent implements batch inference as a periodic processing mode where spam detection occurs in scheduled batches rather than continuously for every single message. This periodic batch processing reduces overall energy consumption while maintaining high productivity by handling multiple messages efficiently during each batch cycle, complementing real-time inference for urgent cases.
Data Source
AI summary
In an example, a text message sent by a first user equipment (UE) and addressed to a second UE is received. In response to receiving the text message, a set of information associated with the text message is determined based upon information determined by a first carrier of the first UE and/or the second UE. The text message is classified as spam or not spam based upon the set of information.