SMS Phishing Detection via Sender Reputation and CTA Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods are inadequate for efficiently detecting phishing attacks through SMS communications, as they lack the secured gateways present in email systems, leading to increased delays and failure in filtering out phishing messages, necessitating a robust, accurate, and fast detection system.
Innovation Solution
A method and system that determine a sender reputation score and classify message patterns, Call To Action (CTA) information, and message patterns using pre-determined data from a database, with a processor configured to detect phishing messages and transmit alert notifications for automatic blocking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If each SMS message is passed through an anti-phishing filter at the base station or switching center, then phishing message detection accuracy is improved, but message processing time increases and delivery is delayed
Solution Approach 1:
The system performs preliminary classification of SMS messages into high-risk and low-risk categories using lightweight heuristics before applying the full anti-phishing filter. This preliminary action filters out obvious benign messages early, allowing only suspicious messages to undergo time-consuming deep analysis, thus reducing overall processing time while maintaining detection accuracy
Solution Approach 2:
The anti-phishing filtering process is segmented into multiple stages: initial heuristic filtering, intermediate risk assessment, and final detailed analysis. This segmentation allows the system to process messages at different levels of scrutiny based on their risk profile, preventing all messages from undergoing the complete time-consuming filtering process
2Measurement precision
If a robust multi-factor detection system is implemented analyzing sender reputation, message patterns, and CTA information, then phishing detection accuracy is improved, but system complexity increases
Solution Approach 1:
The detection system is divided into independent modular components: sender reputation analysis module, message pattern recognition module, CTA information extraction module, and risk synthesis module. Each module handles a specific aspect of phishing detection independently, making the complex system easier to implement, maintain, and update without increasing overall complexity
3Reliability
If real-time phishing message blocking is implemented, then loss prevention is improved, but message routing efficiency decreases
Solution Approach 1:
The system performs real-time phishing detection and classification before message routing decisions are made. By conducting security assessment preliminarily and maintaining a dynamically updated blocklist of known phishing senders and patterns, the system can quickly block identified threats without disrupting the routing of legitimate messages, thus preventing loss while preserving routing efficiency
Data Source
AI summary
Disclosed herein is a method, system and non-transitory computer-readable medium of detecting phishing attacks in Short Message Service (SMS) communications. The method comprises determining a sender reputation score of a sender of an SMS message and Call To Action (CTA) information embedded in the SMS message. Further, the method comprises classifying each of a message pattern, the sender, and the CTA information as one of ‘good’, ‘bad’ and ‘unknown’ based on a comparison with predetermined message pattern data, predetermined sender reputation data, and predetermined CTA information. Subsequently, the method comprises detecting that the SMS message is a ‘phishing’ message based on the classifications of the message pattern, the sender, and the CTA information. Finally, the method comprises transmitting an alert notification to a telecommunication server, upon detecting SMS message the ‘phishing’ message and automatically blocking the ‘phishing’ message from being routed to a recipient.