Spoofed Call Detection via Call Header Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face issues with unwanted telephone calls, such as spam and robocalls, which can lead to financial loss and data theft, and existing caller ID mechanisms are easily spoofed, making it difficult to determine the authenticity of incoming calls.

Innovation Solution

A computer-implemented method that detects incoming phone calls by analyzing caller IDs, determining call characteristics, and applying a trained machine learning model to identify spoofed or robocall calls, assigning labels to indicate whether a call is spoofed or a robocall, and sending these labels to the callee's device for alert or automatic handling.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If caller ID mechanisms are used to determine caller identity, then caller identification is provided, but the caller ID can be easily spoofed reducing reliability

Engineering Contradiction:
Improvecaller identification accuracyVSAvoidcaller identity authenticity
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent introduces an intermediary verification system that analyzes call header information (such as routing paths, network identifiers, and signaling data) between the caller and callee. This intermediary layer validates the authenticity of the caller ID by examining multiple parameters in the call setup process, rather than relying solely on the displayed caller ID. The system acts as a mediator that cross-checks the caller's actual network path against the presented identity, thereby detecting spoofing attempts without requiring changes to existing caller ID infrastructure.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If multiple call analysis parameters are examined to detect spoofing, then detection accuracy is improved, but system complexity increases

Engineering Contradiction:
Improvespoofing detection accuracyVSAvoidanalysis system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the call analysis process into distinct functional modules: call header parsing, parameter extraction, validation rule application, and decision making. Each module handles a specific aspect of the analysis (e.g., extracting routing information, checking network identifiers, validating timezone consistency). This segmentation allows the complex multi-parameter analysis to be implemented as a series of simpler, independent checks that can be processed sequentially or in parallel, reducing the operational complexity while maintaining high detection accuracy.

Inventive Principle:
Principle #1Segmentation

3Reliability

If real-time call header analysis is performed, then spoofed calls are detected promptly, but processing time and computational resources increase

Engineering Contradiction:
Improvespoofing detection timelinessVSAvoidcall setup time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary analysis of call header parameters during the call setup phase, before the actual voice communication begins. By analyzing routing information, network identifiers, and other header data during the initial signaling exchange (SIP/ISUP protocols), the system can detect spoofing attempts in real-time without delaying the call connection. The validation rules are designed to process only essential parameters quickly, allowing most legitimate calls to connect immediately while flagging suspicious patterns for further review.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4099670B1Detection of spoofed calls using call header
Publication Date: 2024.12.18 GOOGLE LLC
  • EP4099670B1 patent drawingFigure 1
  • EP4099670B1 patent drawingFigure 2
  • EP4099670B1 patent drawingFigure 3

AI summary

Implementations described herein relate to methods, systems, and computer-readable media to label incoming phone calls. A method to label an incoming phone call includes detecting the incoming phone call associated with a caller identifier (ID), determining a location associated with the call, and analyzing a call header of the call to determine one or more call characteristics. The method further includes determining, based on the location and the call characteristics, if the location is spoofed and determining, based on the caller ID and the call characteristics, if an access network associated with the call is spoofed. The method further includes applying a trained machine learning model to determine whether the call is a robocall. The method further includes assigning a label to the call that indicates whether the call is a spoofed call or is the robocall and sending the label to a callee device associated with the call.