Behavioral Biometric Fraud Detection via Touch Input Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computing devices, such as mobile handsets, lack effective security measures due to restricted hardware, making them vulnerable to unauthorized access, with traditional methods like smart card readers, OTPs, and voice biometrics being cumbersome or expensive, and there is a need for a user-friendly, automated fraud detection system.
Innovation Solution
A method and system using behavioral biometric algorithms to analyze and categorize user interface input from touch devices, generating a confidence score to distinguish human behavior from machine behavior and detect fraudsters without manual supervision, by processing raw input data into behavioral traits like velocity, acceleration, and sequence behavior, and using Bayesian networks for confidence calculation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional security methods (smart card readers, OTPs, voice biometrics) are added to computing devices, then security is improved, but device complexity and user experience degradation occur
Solution Approach 1:
The patent extracts the security verification function from traditional hardware-based methods (smart cards, OTP tokens) and relocates it to software-based behavioral biometric analysis. The system analyzes touch input sequences, pressure patterns, and interaction timing to identify users, eliminating the need for separate security hardware while maintaining security reliability.
Solution Approach 2:
The patent replaces mechanical/physical security mechanisms (smart card readers, physical OTP tokens) with digital behavioral analysis. Instead of verifying physical possession of security tokens, the system verifies user identity through analysis of touch behavior patterns, substituting physical security infrastructure with software-based biometric verification.
2Reliability
If voice biometric solutions are implemented, then security is improved, but cost and user experience disruption increase
Solution Approach 1:
The patent creates a digital model (profile) of the user's normal touch behavior patterns during registration. During verification, the system compares current touch input sequences against this copied behavioral profile to authenticate the user. This copying approach enables continuous, silent verification without disrupting user interaction, unlike voice biometrics that require active user participation.
Solution Approach 2:
The system performs security verification automatically in the background during normal device use without requiring explicit user action for authentication. The behavioral biometric analysis occurs autonomously as users naturally interact with the device, eliminating the need for users to deliberately provide biometric input and disrupting their workflow.
3Productivity
If automated fraud detection without manual supervision is implemented, then productivity is improved, but measurement precision and system reliability may deteriorate
Solution Approach 1:
The system continuously monitors touch input sequences and compares them against established behavioral profiles, providing real-time feedback on potential fraud. The analysis incorporates multiple feedback dimensions including spatial patterns, temporal sequences, pressure variations, and device orientation changes, enabling automated detection with high precision through multi-parameter verification.
Solution Approach 2:
The patent segments the touch input into discrete sequential events and analyzes each segment's characteristics (position, duration, pressure, angle) independently before synthesizing an overall fraud assessment. This segmentation allows the system to detect subtle anomalies in specific interaction segments while maintaining overall automation, improving both productivity and measurement precision through detailed granular analysis.
Data Source
AI summary
Recording, analyzing and categorizing of user interface input via touchpad, touch screens or any device that can synthesize gestures from touch and pressure into input events. Such as, but not limited to, smart phones, touch pads and tablets. Humans may generate the input. The analysis of data may include statistical profiling of individual users as well as groups of users, the profiles can be stored in, but not limited to data containers such as files, secure storage, smart cards, databases, off device, in the cloud etc. A profile may be built from user/users behavior categorized into quantified types of behavior and/or gestures. The profile might be stored anonymized. The analysis may take place in real time or as post processing. Profiles can be compared against each other by all the types of quantified behaviors or by a select few.