Sonic Liveness Detection for Spoof Prevention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biometric systems face challenges in distinguishing between live individuals and spoofing attempts, particularly with advanced high-definition recording and display technologies, as current anti-spoofing measures are dataset-dependent and have subpar generalization capabilities, and may falsely reject live subjects or accept static reproductions.
Innovation Solution
A multi-stage software-based anti-spoofing and liveness detection technology that combines sonic three-dimensional face sensing with multi-source/multi-path vital detection, using audio signals and photometric signatures to verify the presence of a live person by detecting facial features and pulse, and correlating these with secondary pulse measurements for stronger verification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image texture analysis methods are used to detect spoofing, then spoof detection capability is improved, but reliability deteriorates due to dataset dependency and poor generalization
Solution Approach 1:
The patent replaces image texture analysis (optical/electromagnetic field analysis) with acoustic field analysis using ultrasonic waves. The system emits ultrasonic signals that interact with the target's physical properties (density, elasticity, surface geometry) to generate echo patterns, which are more reliable indicators of liveness than image textures. This substitution moves from analyzing visual artifacts to analyzing physical material properties.
Solution Approach 2:
The patent changes the detection parameter from image texture characteristics to acoustic echo characteristics. By using ultrasonic waves with specific frequencies and analyzing the reflected echo patterns, the system detects physical properties such as tissue density, surface compliance, and geometric structure that are inherent to living beings and difficult to replicate in spoofs.
2Reliability
If multi-stage verification with vital detection is implemented, then authentication accuracy is improved, but device complexity increases
Solution Approach 1:
The patent makes the mobile device perform multiple functions using existing components: the speaker emits ultrasonic signals, the microphone receives echoes, and the processor analyzes acoustic patterns. This multi-functionality approach allows liveness detection without adding dedicated hardware, reducing complexity while maintaining accuracy.
Solution Approach 2:
The system uses the device's own acoustic components (speaker and microphone) to perform liveness detection, rather than requiring separate sensing hardware. The device serves itself by utilizing its existing audio infrastructure for both communication and authentication purposes.
3Reliability
If acoustic signals are used for three-dimensional face sensing, then spoof detection reliability is improved, but difficulty of detecting and measuring increases due to signal processing complexity
Solution Approach 1:
The patent performs preliminary processing of the acoustic echo signals by filtering out background noise and isolating the relevant frequency bands before analysis. The system prepares the signal data in advance by converting raw acoustic inputs into structured features that are easier to analyze for liveness detection.
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 detects spoofing attempts regardless of image quality and environment, providing accurate authentication by confirming the presence of a live individual through recognizable physical properties and vital signs, reducing false rejections and acceptances.
Implementation Method 1
emitting, using an audio output component of a user device, one or more audio signals; receiving, using an audio input component of the user device, one or more reflections of the audio signals off a target
Implementation Method 2
identifying a first pulse of the target using remote photoplethysmography
Data Source
Figure 1A~1C
Figure 2
Figure 3
AI summary
Spoof-detection and liveness analysis is performed using a software-based solution on a user device, such as a smartphone having a camera, audio output component (e.g., earpiece), and audio input component (e.g., microphone). One or more audio signals are emitted from the audio output component of the user device, reflect off a target, and are received back at the audio input component of the device. Based on the reflections, a determination is made as to whether the target is comprised of a three-dimensional face-like structure and/or face-like tissue. Using at least this determination, a finding is made as to whether the target is likely to be spoofed, rather than a legitimate, live person.