Former-Device Authentication With Reliability-Based Question Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing authentication methods using device-based questions can be confusing and time-consuming for users, especially when they have used a variety of devices for brief periods or borrowed devices, leading to frustration and potential unauthorized access.
Innovation Solution
A computing device uses machine learning models to determine the reliability of devices based on user transaction and login history, generating modified device choices by excluding devices with low reliability levels, thereby creating more memorable and secure authentication questions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If device-based authentication questions include all devices from user history, then security is improved by including more potential answers, but user experience deteriorates due to confusion and time consumption
Solution Approach 1:
The patent extracts and excludes devices with low reliability scores from the authentication question options. The system calculates a reliability score for each device based on factors like usage frequency, recency, and user recognition, then removes devices below a threshold from the candidate answers, reducing confusion while maintaining security.
Solution Approach 2:
The patent changes the parameter of device inclusion from binary (included/excluded) to continuous (reliability scoring). By assigning reliability scores based on multiple factors and using these scores to weight or filter device options, the system optimizes the balance between security and user experience.
2Productivity
If authentication questions use personal information from databases, then question generation is automated, but security deteriorates because answers become guessable
Solution Approach 1:
The patent introduces device usage history as an intermediary between automated question generation and secure authentication. Instead of directly using personal information from databases, the system mediates through actual device usage patterns, creating questions about devices the user has genuinely used, which are harder to guess but still automated to generate.
Solution Approach 2:
The system uses the user's own device usage history to generate authentication questions, allowing the user to authenticate themselves through knowledge of their own behavior patterns rather than relying on external personal information databases.
3Adaptability or versatility
If authentication questions include devices used briefly or borrowed, then comprehensiveness is improved, but reliability deteriorates due to user inability to recall
Solution Approach 1:
The patent changes the parameter of device inclusion from equal weighting to reliability-based weighting. By calculating reliability scores that account for usage duration, frequency, and recency, the system dynamically adjusts which devices are included and how they are weighted in authentication questions, optimizing for both comprehensiveness and recall accuracy.
Data Source
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.