Behavioral Authentication via Typing Gait and Spending Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems require user involvement in authentication processes, which can be labor-intensive and vulnerable to data breaches, necessitating a method to eliminate user authentication involvement through system-to-system credential exchange.
Innovation Solution
A machine learning-based system evaluates user actions and predicts potential misappropriation by monitoring typing gait, natural language processing, and past spending patterns to create a database of user idiosyncrasies, allowing authentication without traditional password or pin entry by matching user actions with stored idiosyncrasies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional password or pin authentication is used, then user authentication can be performed, but user burden increases and security is vulnerable to data breaches
Solution Approach 1:
The system performs self-authentication by automatically comparing user actions against stored idiosyncrasies without requiring user involvement in the authentication process. The authentication credentials (typing gait, touch screen gait, angle of viewing, location) are captured and verified automatically, eliminating the need for users to manually enter passwords or PINs while maintaining security through biometric pattern recognition.
2Extent of automation
If system-to-system authentication credential exchange is implemented, then user involvement is eliminated, but system complexity increases
Solution Approach 1:
The system captures and stores user action idiosyncrasies (typing gait, touch screen gait, angle of viewing, location) in advance during normal device usage. This preliminary capture of biometric data allows the system to perform automated authentication later by simply comparing new user actions against the pre-stored idiosyncrasies, eliminating the need for complex real-time authentication protocols while maintaining high automation levels.
3Reliability
If user action monitoring is implemented to prevent misappropriation, then security is improved, but processing time increases
Solution Approach 1:
The system continuously monitors and captures user actions (typing gait, touch screen gait, angle of viewing, location) during normal device usage without interrupting the user's workflow. This continuous capture of biometric data in the background allows for real-time authentication and misappropriation prevention while maintaining seamless user experience and minimal processing time, as the authentication data is already captured and ready for comparison.
Data Source
AI summary
Embodiments of the invention are directed to systems, methods, and computer program products for a scheme evaluation authentication system to evaluate user action and machine learned pattern recognition for misappropriation activity prevention. In this way, bot and token deployment is utilized for identification of user actions to generate a user idiosyncrasy database. Using the database, the system creates a real-time scheme evaluation authentication for user authentication upon user attempted authentications. As such, a user may by authenticate irrespective of user inputs, but instead based on a match of user actions at the authentication location in real-time compared to the idiosyncrasy database.