Mobile Device Fraud Detection via Usage Pattern Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Smartphones lack effective local detection mechanisms for fraudulent activity and unauthorized access, leading to potential theft and misuse of personal and work-related information, with existing security measures being inconvenient or prone to false positives and not adequately preventing data breaches.

Innovation Solution

A fraud detection module within mobile devices that builds historical usage patterns, monitors parameters, and computes confidence scores to differentiate between authorized and unauthorized usage, enabling local detection and remedial actions such as locking the device or alerting the user.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If lock code features are implemented to prevent unauthorized access, then security is improved, but ease of operation deteriorates due to frequent pin number entry requirements

Engineering Contradiction:
ImprovesecurityVSAvoidease of operation
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system performs preliminary actions by continuously monitoring usage patterns in the background and pre-computing fraud detection models before unauthorized access occurs. This allows the system to detect fraud without requiring user intervention or manual security checks, thus maintaining both security and ease of operation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The fraud detection system serves itself by automatically monitoring its own usage patterns, computing fraud indicators, and triggering security measures without external intervention. The system self-regulates security based on detected anomalies in usage behavior, eliminating the need for frequent manual pin entries while maintaining security

Inventive Principle:
Principle #25Self-service

2Ease of operation

If biometric access protection features are implemented, then ease of operation is improved, but reliability deteriorates due to false positives enabling unauthorized access

Engineering Contradiction:
Improveease of operationVSAvoidsecurity
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system implements feedback by continuously monitoring usage patterns after biometric authentication and comparing actual usage behavior against expected patterns. When deviations are detected, the system triggers additional security measures such as requiring pin verification or alerting the user, thus correcting false positives while maintaining ease of operation for legitimate users

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system applies preliminary anti-action by preparing counter-measures in advance for potential false positives. Fraud detection models are pre-computed and security protocols are pre-established so that when unauthorized access is detected, the system can immediately respond with appropriate counter-actions such as locking the device or alerting the user

Inventive Principle:
Principle #9Preliminary anti-action

3Reliability

If remote wipe solution is implemented, then security is improved, but loss of time increases due to delayed response when device is stolen

Engineering Contradiction:
ImprovesecurityVSAvoidresponse time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by continuously monitoring usage patterns and detecting fraud in real-time before the device is stolen or remotely wiped. This early detection allows immediate local response actions to be taken, eliminating the delay associated with remote wipe solutions that require user awareness and communication connectivity

Inventive Principle:
Principle #10Preliminary action

4Ease of operation

If automatic password storage features are implemented, then ease of operation is improved, but security deteriorates by obviating password protection safeguards

Engineering Contradiction:
Improveease of operationVSAvoidsecurity
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system implements feedback by monitoring usage patterns related to password storage and automatic login features. When fraud is detected, the system can dynamically adjust security measures to disable automatic password storage or require additional verification, thus maintaining ease of operation for legitimate users while preventing security compromises

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3245806B1Automatic intelligent local device fraud detection
Publication Date: 2019.09.04 CITRIX SYSTEMS INC
  • EP3245806B1 patent drawingFigure 1
  • EP3245806B1 patent drawingFigure 2
  • EP3245806B1 patent drawingFigure 3

AI summary

Methods, systems, computer-readable media, and apparatuses may provide a mobile device with the ability to locally detect fraudulent activity by an unauthorized user. A mobile device may include a fraud detection module that may build a historical usage pattern of a user of the mobile device. The fraud detection module may monitor usage of the mobile device for multiple parameters and record events pertaining to the parameters. Periodically or in response to each event, the fraud detection module may compute a current usage pattern using each of the current parameter values. The fraud detection module may compare the current usage pattern with the historical usage pattern and may use the comparison result to compute a confidence score. The fraud detection module may then compare the confidence score with a preset confidence score to determine whether fraudulent activity is occurring at the mobile device.