Device-History Authentication with Reliability-Based Question Filtering

Solution Overview

Problem

Existing device-based authentication methods are unreliable and confusing for users, particularly when they use devices infrequently or for brief periods, leading to frustration and potential security vulnerabilities.

Innovation Solution

A computing device trains machine learning models using account records to determine device reliability, generating authentication questions based on a modified set of reliable devices, excluding those with low reliability levels to enhance user accessibility and security.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If all devices from user history are included in authentication questions, then security is improved by reducing guessability, but user experience deteriorates due to confusion and frustration

Engineering Contradiction:

Improveauthentication securityVSAvoiduser experience

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system performs preliminary analysis of device history data before generating authentication questions. It pre-identifies frequently used devices and pre-filters out rarely used devices, so that when authentication is needed, only relevant devices are presented to the user. This preliminary sorting action resolves the contradiction by preparing the device list in advance to balance security and usability.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies different inclusion criteria to different devices based on their individual usage characteristics. Frequently used devices are included in authentication questions while rarely used devices are excluded. This local differentiation approach ensures that each device is treated according to its specific usage pattern, maintaining security for important devices while improving user experience by excluding confusing ones.

Inventive Principle:

Principle #3Local quality

2Ease of operation

If frequently used devices are excluded from authentication questions, then user experience improves by reducing confusion, but security deteriorates due to increased guessability

Engineering Contradiction:

Improveuser experienceVSAvoidauthentication security

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system performs preliminary analysis of device history data before generating authentication questions. It pre-identifies frequently used devices and pre-filters out rarely used devices, so that when authentication is needed, only relevant devices are presented to the user. This preliminary sorting action resolves the contradiction by preparing the device list in advance to balance security and usability.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies different inclusion criteria to different devices based on their individual usage characteristics. Frequently used devices are included in authentication questions while rarely used devices are excluded. This local differentiation approach ensures that each device is treated according to its specific usage pattern, maintaining security for important devices while improving user experience by excluding confusing ones.

Inventive Principle:

Principle #3Local quality

3Ease of operation

If personal information questions are used for authentication, then ease of operation improves, but security deteriorates due to obtainability and guessability

Engineering Contradiction:

Improveauthentication simplicityVSAvoidauthentication security

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system extracts device usage information from transaction and login history data, separating it from traditional personal information questions. Instead of asking about personal facts that can be guessed or obtained through social engineering, the system presents objective device identification questions based on actual usage patterns. This extraction of authentication criteria from personal information to behavioral data resolves the security-usability contradiction.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Device usage history serves as an intermediary between the user and the authentication system. Rather than directly questioning personal information, the system uses device usage patterns as an intermediate layer that objectively verifies user identity. This intermediary approach maintains security while improving ease of operation, as users can answer device-based questions more reliably than personal information questions.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20250298882A1Computer authentication using knowledge of Former devices

Publication Date: 2025.09.25 CAPITAL ONE SERVICES LLC

AI summary

Methods, systems, and apparatuses are described herein for improving computer authentication processes through computer-based authentication in a manner that uses knowledge of former devices. A computing device may train a machine learning model to output an indication of device reliability data associated with a particular device. The computing device may receive a request for access to an account from a user. The computing device may receive account data and provide the account data to the trained machine learning model. The computing device may receive data indicating device reliability for a set of devices from the machine learning model. The computing device may generate a modified set of device choices for the user by excluding devices having reliability levels below a threshold value. An authentication question may be generated, and access to the account may be provided based on a response to the authentication question.