Voice Authentication With One-Time Passcode Against Spoofing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing authentication methods, particularly voice biometrics, are vulnerable to spoofing attacks such as replay and synthesis attacks, which compromise security by mimicking or synthesizing legitimate user voices.

Innovation Solution

Integrating voice biometric authentication with a one-time passcode and analyzing timing information, where the user is authenticated only if both the voice and the text extracted from the voice recording match the expected text and timing criteria, and the passcode is sent to a registered device, adding a personal possession factor.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice biometric authentication is used, then authentication convenience is improved, but security against spoofing attacks deteriorates

Engineering Contradiction:
Improveauthentication convenienceVSAvoidsecurity against spoofing attacks
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent combines voice biometric authentication with one-time passcode verification and timing analysis into a unified authentication system. The voice authentication module extracts biometric features from the audio signal, while simultaneously a passcode validation module verifies the uniqueness of the spoken phrase, and a timing analysis module checks the response time. All three modules must succeed for authentication to pass, creating a multi-layered security mechanism that maintains convenience while dramatically improving resistance to spoofing attacks.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces timing parameters as an additional authentication criterion. The system measures the response time between presenting the passcode and detecting the user's speech response, comparing it against expected human response ranges. This temporal parameter change adds a dynamic dimension to authentication that is difficult for spoofing systems to replicate, as synthetic voice generation and replay attacks cannot easily match natural human response timing.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If multi-factor authentication is implemented, then security is improved, but device complexity increases

Engineering Contradiction:
ImprovesecurityVSAvoidauthentication system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent designs the authentication system to process multiple authentication factors through a unified audio interface. The same audio input signal is simultaneously analyzed by voice biometric modules, passcode validation modules, and timing analysis modules. This multi-functional approach allows the system to implement multi-factor authentication without requiring separate input devices or interfaces for each factor, thereby reducing overall system complexity while maintaining high security.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent uses the user's speech as an intermediary that carries multiple authentication signals simultaneously. The spoken passcode serves as both the authentication challenge response and the biometric sample, while the timing of the speech provides the temporal verification factor. This intermediary approach consolidates multiple authentication mechanisms into a single user action, simplifying the interface while implementing robust multi-factor security.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If voice authentication is performed, then authentication speed is improved, but vulnerability to replay attacks increases

Engineering Contradiction:
Improveauthentication speedVSAvoidvulnerability to replay attacks
Core Design Contradiction:
ProductivityVSObject-affected harmful factors

Solution Approach 1:

The patent implements periodic authentication challenges where a unique passcode is presented to the user for each authentication attempt. This periodic variation ensures that even if an attacker records a legitimate user's voice response, the recorded data becomes obsolete for subsequent authentication attempts. The system maintains fast authentication by automatically generating and validating new passcodes in real-time, preventing replay attacks while preserving authentication speed.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The patent performs preliminary validation of the spoken passcode against the expected unique string before completing authentication. The system compares the extracted text from the audio signal with the predetermined passcode in real-time, and only proceeds with full authentication if they match. This preliminary check acts as a gatekeeper that immediately rejects replayed or synthesized voices that do not contain the correct unique passcode, preventing replay attacks while maintaining rapid authentication for legitimate users.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4170527B1An authentication method and system
Publication Date: 2025.11.26 VALIDSOFT LTD
  • EP4170527B1 patent drawingFigure 1
  • EP4170527B1 patent drawingFigure 2A~2B
  • EP4170527B1 patent drawingFigure 3A

AI summary

An authentication method, comprising: obtaining a string; receiving an audio signal; performing speech recognition on the audio signal to extract text; and performing authentication of a user, the authentication comprising: comparing the extracted text and the string; and performing voice authentication of the user based on the audio signal.