Server-Based Caller Verification Using Turing Tests

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Communication networks face disturbances and financial losses due to automatically generated caller attacks, such as 'call bombs,' 'Wangiri,' and 'CLI spoofing,' which overwhelm lines and incur excessive charges, as existing methods like SIM boxing and OTT firewalls are inadequate in distinguishing human from machine callers.

Innovation Solution

A method and system that utilize a server-based checking function to evaluate communication behavior, employing a Turing test to verify if callers are human, and modify or block calls based on the test results, preventing fraudulent forwarding and protecting communication partners from harassment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional SIM boxing methods or OTT firewalls are used to block caller attacks, then some protection is provided, but they cannot distinguish between human and machine callers, allowing automated attacks to bypass them

Engineering Contradiction:
Improveprotection effectivenessVSAvoiddetection capability
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

A server-based checking function acts as an intermediary between the communication network and callers. This intermediary evaluates communication behavior and performs Turing tests to distinguish human from machine callers, enhancing protection effectiveness without requiring complex modifications to existing network infrastructure

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces traditional mechanical filtering methods (SIM boxing, OTT firewalls) with an intelligence-based system using Turing tests and behavior evaluation. This substitution enables the system to distinguish human from machine callers through cognitive assessment rather than simple pattern matching

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Object-affected harmful factors

If a Turing test is implemented to verify human callers, then automated attacks can be blocked, but the system complexity and processing time increase

Engineering Contradiction:
Improveautomated attack blockingVSAvoidsystem complexity
Core Design Contradiction:
Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The checking function performs preliminary evaluation of communication behavior before the actual Turing test. By analyzing communication patterns in advance, the system can identify suspicious callers and apply Turing tests selectively, reducing overall system complexity while maintaining automated attack blocking capability

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system applies Turing tests partially rather than to all callers. The checking function evaluates communication behavior and applies security checks only to suspicious cases, avoiding the excessive complexity of universal Turing testing while still effectively blocking automated attacks

Inventive Principle:
Principle #16Partial or excessive action

3Measurement precision

If communication behavior is evaluated for all callers, then detection accuracy improves, but processing time and network load increase

Engineering Contradiction:
Improvedetection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The checking function performs behavior evaluation selectively rather than universally. It monitors communication patterns and applies detailed detection only to suspicious callers, maintaining high detection accuracy while minimizing processing time and network load for legitimate users

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system performs preliminary monitoring of communication behavior for all callers but applies intensive evaluation only when anomalies are detected. This preliminary action allows the system to maintain high detection accuracy while avoiding the time cost of evaluating every caller in detail

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3410664B1Method for protecting at least one communication partner in a technical communication network
Publication Date: 2021.06.30 DEUTSCHE TELEKOM AG
  • EP3410664B1 patent drawingFigure 1
  • EP3410664B1 patent drawingFigure 2
  • EP3410664B1 patent drawingFigure 3

AI summary

The present invention relates to a method for protecting at least one communication partner in a communication network from automatically generated caller attacks, in which at least one participant (23) of the communication network (20) contacting the at least one communication partner is checked by means of a verification function implemented on at least one server (31) in communicative connection with the communication network (20), which evaluates a communication behavior of the participant (23) and/or a communication behavior of the at least one communication partner (24) contacted by the participant (23).and in which, depending on the result of an evaluation of the communication behavior of the participant (23) and/or the communication behavior of the at least one communication partner (24) contacted by the participant (23) using the verification function, an automatic security check of the participant (23) is carried out by means of a security function implemented on the at least one server (31), wherein the security function includes a Turing test to verify whether the participant (23) is a human being, and in which the forwarding of the participant (23) to the at least one communication partner (24) in the communication network (20) is handled depending on a result of the security check. Furthermore, the present invention relates to a corresponding protection system.