Smart Device Fake Voice Command Detection via Triangulation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Smart devices lack effective authentication methods for voice commands, making them vulnerable to unauthorized access through fake voice commands generated by light beams, such as those from lasers, which can lead to data privacy issues and security breaches.

Innovation Solution

A system and method that uses a controller to detect fake voice commands by comparing sound characteristics from multiple microphones, triangulating the source of sound, and verifying user proximity through WiFi reflection and device authentication, to differentiate between legitimate and unauthorized voice commands.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If voice commands are accepted without authentication, then ease of operation is improved, but security is worsened

Engineering Contradiction:
Improvevoice command operationVSAvoidsecurity
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent introduces an intermediary authentication system that mediates between the voice command input and the device execution. Multiple microphones capture voice commands from different positions, and the system processes these signals through triangulation and correlation analysis to verify authenticity before executing commands, thus preventing laser-induced fake commands while maintaining convenient voice operation

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If multiple microphones are used for detection, then measurement precision is improved, but device complexity is worsened

Engineering Contradiction:
Improvevoice source localizationVSAvoidmicrophone array system
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent transitions from single-point voice detection to three-dimensional spatial voice analysis by deploying multiple microphones at different positions within the device. This dimensional expansion enables triangulation of voice sources and correlation analysis across spatial dimensions, achieving precise localization and fake command detection while managing complexity through systematic signal processing

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Effectively prevents unauthorized access by accurately identifying and notifying users of fake voice commands, thereby enhancing the security and privacy of smart devices and associated systems.

Implementation Method 1

The diaphragm and a fixed back plate located within the smart device work as a parallel-plate capacitor whose capacitance changes as the diaphragm deforms in response to different sound pressures

Methodology Applied
Scientific EffectCapacitance: Capacitance

Implementation Method 2

Projecting an amplitude-modulated light beam via a laser onto the microphone may also cause movement of the diaphragm. Varying the amplitude of the light beam may cause different degrees of movement of the diaphragm, thereby causing the microphone to interpret the different degrees of movement of the diaphragm as different electrical signals

Methodology Applied
Scientific EffectLight pressure: Radiation Pressure

Implementation Method 3

triangulating the source of sound, and verifying user proximity through WiFi reflection

Methodology Applied
Scientific EffectReflection: Reflection

Data Source

PatentUS12183339B1Systems and methods for detecting fake voice commands to smart devices
Publication Date: 2024.12.31 UNITED SERVICES AUTOMOBILE ASSOCIATION (USAA)
  • US12183339B1 patent drawing
  • US12183339B1 patent drawing
  • US12183339B1 patent drawing

AI summary

The present disclosure relates to detecting the use of fake voice command to activate microphones of smart devices. In one embodiment, sound characteristics associated with an audio signal from a microphone of smart device may be compared with other microphones of the smart device in order to detect fake voice commands. In another embodiment, sound characteristics associated with the audio signal from the microphone may be compared with a threshold range of stored sound characteristics in order to detect fake voice commands. In some embodiments, a controller may triangulate a position associated with a source of a sound in order to detect a fake voice command. In a further embodiment, a controller may verify that a user or associated electronic device are near a smart device to authorize a voice command.