Trust-Adaptive Fingerprint and Face Scanning for Low-Energy Authentication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional biometric systems face challenges with increased energy consumption, complexity, and latency due to the use of multiple biometric traits, and reliance on cloud servers for processing, which is inefficient for IoT devices with limited resources.
Innovation Solution
An energy-efficient multi-biometric authentication system incorporating a trust management system and decision-level multi-biometric approach, utilizing a fingerprint scanner and camera with a trust database to manage trust values based on biometric matches, reducing energy consumption and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple biometric traits are used to improve authentication accuracy, then authentication reliability is improved, but energy consumption and system complexity increase
Solution Approach 1:
The system dynamically adjusts the number of biometric traits used for authentication based on the user's trust value. Trusted users are authenticated using fewer biometric traits (reducing energy consumption), while less trusted users undergo more comprehensive verification (improving security). This dynamic adaptation resolves the contradiction by making the system flexible rather than static.
Solution Approach 2:
The system changes the authentication parameter (number of biometric traits) based on the trust value parameter. By modifying which biometric traits are used and how many are required based on the user's trust level, the system optimizes the balance between authentication accuracy and energy consumption for each user.
2Reliability
If multiple biometric traits are used to improve authentication accuracy, then authentication reliability is improved, but device complexity increases
Solution Approach 1:
The system dynamically adjusts the number of biometric traits used for authentication based on the user's trust value. Trusted users are authenticated using fewer biometric traits (reducing system complexity), while less trusted users undergo more comprehensive verification (improving security). This dynamic adaptation resolves the contradiction by making the system flexible rather than static.
Solution Approach 2:
The authentication process is segmented into different levels based on user trust. The system divides the authentication complexity into manageable segments, allowing trusted users to skip certain verification steps while ensuring thorough checking for less trusted users, thus reducing overall system complexity.
3Device complexity
If cloud servers are used for processing and storage to reduce local resource requirements, then device complexity is reduced, but transmission cost and latency increase
Solution Approach 1:
The system performs preliminary actions by pre-computing and storing trust values and authentication results locally on the edge device. This eliminates the need for continuous cloud communication for authentication decisions, reducing latency while maintaining the ability to leverage cloud resources for complex computations when necessary.
Solution Approach 2:
The edge device acts as an intermediary between the user and the cloud server. It handles routine authentication tasks locally using stored trust information, only communicating with the cloud for complex computations or when trust values need updating, thus reducing latency while maintaining cloud resource access.
4Adaptability or versatility
If conventional client-server paradigm is used with SBC RPi as server, then system scalability is improved, but energy consumption increases due to continuous operation
Solution Approach 1:
The system uses periodic action by waking the SBC RPi server from low-power state only when authentication requests are received. Instead of continuous operation, the server enters sleep mode between requests, reducing energy consumption while maintaining scalability through the same hardware architecture.
Solution Approach 2:
The server operates dynamically, switching between active and sleep states based on authentication demand. This dynamic operation allows the system to maintain scalability for multiple clients while significantly reducing energy consumption during periods of low activity.
Data Source
AI summary
A computer system and method having an energy-efficient multi-biometric authentication that includes a fingerprint scanner, a camera, a memory, and a processing circuitry. The processing circuitry reads a predefined probability from the memory and generates a random number. The processing circuitry inputs a user ID and retrieves a trust value for the user from a trust database. The processing circuitry obtains a scanned user fingerprint using a fingerprint scanner and obtains a captured user face using the camera. The processing circuitry applies a reward to the trust value to increase the trust value when the scanned user fingerprint is substantially the same as the stored user fingerprint and the captured user face is substantially the same as a stored user face in a face database, store the trust value as the cumulative trust value for the user, and authenticate the user to allow access to the computer system.