Multi-Modal Authentication Using Voice and Touch Sequencing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional passphrase authentication methods, such as typing or voice-only passphrases, are insecure in public settings as they can be easily compromised, and typing on small virtual keyboards is cumbersome.

Innovation Solution

A method using a device with a touch interface and audio receiver that requires users to speak a passphrase while interacting with the device's interface, correlating verbal words with specific touch interactions or inflection points to provide multi-factor authentication, ensuring correct pairing for access.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice-only passphrase authentication is used, then ease of operation is improved, but security is worsened due to easy eavesdropping in public settings

Engineering Contradiction:

Improveease of operationVSAvoidsecurity

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent combines voice passphrase input with tactile interface interactions (taps, swipes, or presses) to create a multi-modal authentication system. The voice component maintains ease of operation while the tactile component adds security by requiring coordinated physical actions that are harder to replicate through eavesdropping alone.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The authentication process is segmented into multiple independent components: voice passphrase delivery, tactile interaction sequence, and temporal coordination. Each component can be independently verified, and the segmentation allows the system to validate that the voice input and tactile actions are properly synchronized, preventing replay attacks.

Inventive Principle:

Principle #1Segmentation

2Reliability

If typing passphrase on virtual keyboard is used, then security is improved, but ease of operation is worsened due to cumbersomeness on small keyboards

Engineering Contradiction:

ImprovesecurityVSAvoidease of operation

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The patent replaces the mechanical typing action on a virtual keyboard with a voice-based passphrase delivery system. This substitution eliminates the need for precise manual input while maintaining security through the addition of required tactile interactions, thereby improving ease of operation without sacrificing security.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The tactile interface serves multiple functions: it provides the authentication input channel, establishes temporal synchronization with voice input, and creates a unique interaction pattern. This multi-functionality allows the same interface element to address both ease of operation and security requirements simultaneously.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Reliability

If multi-factor authentication with touch and voice is used, then security is improved, but device complexity is worsened

Engineering Contradiction:

ImprovesecurityVSAvoiddevice complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system uses the device's existing audio receiver and touch interface components to perform authentication, rather than requiring separate dedicated hardware for each factor. The audio receiver serves both media playback and voice authentication functions, while the touch interface handles both user interaction and authentication input, reducing overall system complexity.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent implements a registration phase where the system pre-stores the user's voice passphrase and associated tactile interaction patterns. During authentication, the system only needs to verify against these pre-stored patterns, simplifying the real-time processing requirements and reducing the complexity of the authentication algorithm.

Inventive Principle:

Principle #10Preliminary action

4Ease of operation

If passphrase is spoken aloud, then ease of operation is improved, but security is worsened due to passphrase being overheard in public places

Engineering Contradiction:

Improveease of operationVSAvoidsecurity compromise

Core Design Contradiction:

Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The tactile interaction sequence serves as an intermediary that binds the voice passphrase to a unique physical action pattern. Even if an eavesdropper captures the voice passphrase, they cannot replicate the authentication without also performing the correct sequence of taps, swipes, or presses in the correct temporal alignment with the voice input.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent adds a spatial and temporal dimension to the authentication process by requiring coordinated tactile actions synchronized with voice input. This transforms the authentication from a purely auditory challenge into a multi-dimensional problem that combines temporal sequencing, spatial positioning of touch actions, and acoustic signal processing, making eavesdropping insufficient for compromise.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS10073959B2Secure authentication of users of devices using tactile and voice sequencing with feedback

Publication Date: 2018.09.11 KYNDRYL INC

AI summary

A method for securely authenticating users of a device which uses pairings of a verbal passphrase and user interactions. The user interactions may be finger position on an interface of the device, number of taps on the interface of the device, or touching of the interface in a predefined area. Alternatively, the user can provide a verbal passphrase with inflection points.