Behavioral Authentication Score Fusion for Changing User Activity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Behavioral biometric authentication requires a learning period before achieving sufficient accuracy, and significant lifestyle changes due to events like moving, job changes, or travel can hinder its effectiveness.
Innovation Solution
An authentication system that calculates a target authentication score based on a habitual score derived from user activity and a use occasion score from history, allowing secure authentication even during changes in activity patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If behavioral biometric authentication is used, then authentication can be performed without active user operation, but a learning period is required and authentication accuracy decreases when activity patterns change
Solution Approach 1:
The authentication score is segmented into two independent components: a habitual score based on learned activity patterns and a use occasion score based on contextual information. This segmentation allows the system to maintain accuracy during activity changes by relying more on the use occasion score, while still benefiting from the ease of operation provided by behavioral biometric authentication.
Solution Approach 2:
The system dynamically adjusts the weightings between the habitual score and use occasion score based on detected activity pattern changes. When changes are detected, the system shifts parameters to prioritize the use occasion score, maintaining authentication accuracy while preserving the hands-free operation capability.
2Ease of operation
If behavioral biometric authentication is used, then hands-free authentication is achieved, but a learning period is required before sufficient accuracy is achieved
Solution Approach 1:
The system performs preliminary learning of user activity patterns during normal operation to build the habitual score model. This preliminary action enables the system to achieve hands-free authentication quickly after the learning period by using the pre-built model, eliminating the need for continuous learning during critical authentication moments.
Solution Approach 2:
The system creates a copy of the user's habitual activity pattern as a reference model. This copied habitual score serves as a baseline that can be quickly compared against current activity data, reducing the effective learning time needed while maintaining hands-free operation capability.
3Ease of operation
If authentication is performed during activity changes, then user convenience is maintained, but recognition accuracy is insufficient
Solution Approach 1:
The use occasion score acts as an intermediary that bridges the gap between habitual patterns and current activity. It incorporates contextual information about the specific situation, allowing the system to maintain both user convenience during activity changes and sufficient recognition accuracy by mediating between the learned habits and current behavior.
Solution Approach 2:
The system dynamically adjusts the authentication approach based on detected activity changes. When changes are detected, it shifts the balance between habitual and use occasion scores, maintaining recognition accuracy while preserving user convenience during transitions such as moving or job changes.
Data Source
AI summary
There are provided an information processing device, an information processing method, and a program that can reduce disadvantages of a user during use of authentication based on a user's activity. The information processing device includes a control unit that performs: processing of calculating a target authentication score based on a habitual score calculated based on an activity of a user and habitual information of the user, and a use occasion score calculated based on a target use history of the user; and processing of determining based on the target authentication score whether authentication at a target succeeds or fails.