Voice Authentication System Using Dynamic Verification Phrases
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network-based authentication systems using voice biometric data face challenges in accurately distinguishing between live and fraudulent biometric data, leading to low authentication accuracy rates due to spoofing attempts, as imposters can easily obtain and misuse genuine voice biometric data.
Innovation Solution
The system enhances authentication accuracy by determining and using new verification phrases, capturing biometric data, and storing it in an enrollment registry, making it difficult for imposters to anticipate the authentication data requirement and reducing fraudulent transactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If text independent voice recognition techniques are used for liveness detection, then spoofing resistance is improved, but authentication accuracy deteriorates
Solution Approach 1:
The authentication process is divided into multiple independent phases: enrollment phase where voice biometric data is captured and stored, and authentication phase where the stored data is compared against the claimed identity. This segmentation allows the system to maintain high accuracy by using text-dependent recognition during enrollment while using text-independent methods during authentication, resolving the contradiction between accuracy and spoofing resistance.
Solution Approach 2:
The system performs preliminary action by capturing and storing voice biometric data during the enrollment phase before the actual authentication occurs. This preliminary data collection enables the system to establish a baseline for accurate authentication while using text-independent techniques during the actual authentication to prevent spoofing, thus resolving the accuracy-reliability contradiction.
2Ease of operation
If all individuals are prompted to recite the same phrase, then ease of operation is improved, but security deteriorates due to predictable authentication data
Solution Approach 1:
The system dynamically adapts the verification phrase based on the user's identity and the authentication context. Instead of using a fixed phrase for all users, the system selects phrases from a predefined set or generates unique phrases for each user, making the authentication data unpredictable for imposters while remaining easy to remember for legitimate users, thus resolving the security-convenience contradiction.
Solution Approach 2:
The system changes the parameter of the verification phrase based on user identity and authentication context. By varying the phrase selection based on user characteristics and authentication scenarios, the system maintains ease of operation for authorized users while preventing predictability for imposters, resolving the contradiction between operational ease and security.
Data Source
AI summary
A method for enhancing the accuracy performance of authentication systems includes determining an authentication data requirement for a desired transaction and at least one new verification phrase. The method also includes capturing authentication data from a user with a communications device in accordance with the authentication data requirement, and capturing biometric data of the at least one new verification phrase from the user with the communications device. Moreover, the method includes adding the determined at least one new verification phrase to an enrollment phrase registry and storing the biometric data captured for the at least one new verification phrase in an enrollment data record of the user after successfully authenticating the user.