Biometric Authentication Using Pseudo-Random Illumination Patterns

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Biometric authentication systems, particularly facial recognition, are vulnerable to spoofing and replay attacks, where malicious entities attempt to trick the system into incorrectly identifying an unauthorized user by presenting pre-captured images or invalid data.

Innovation Solution

The implementation of a pseudo-random sequence of image capture modes and a secret illumination pattern, where the device generates and verifies a sequence of two-dimensional and three-dimensional image captures, and uses a probing pattern to ensure that only authentic and current biometric data is accepted for authentication.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional biometric authentication is used, then user convenience is improved, but security against spoofing and replay attacks deteriorates

Engineering Contradiction:
Improveuser convenienceVSAvoidsecurity against spoofing and replay attacks
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system dynamically changes the illumination pattern between different capture modes (2D and 3D) in a pseudo-random sequence, making the authentication process adaptive and unpredictable. This dynamic switching prevents static spoofing attempts while maintaining smooth user interaction.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system employs periodic switching between different image capture modes (2D with flood illumination, 3D with depth illumination) in a predetermined pseudo-random sequence. This periodic action creates multiple verification opportunities while maintaining user convenience through automated operation.

Inventive Principle:
Principle #19Periodic action

2Reliability

If multiple image capture modes are used, then security is improved, but device complexity increases

Engineering Contradiction:
Improvesecurity verificationVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The camera unit is designed to perform multiple functions - capturing both 2D images with flood illumination and 3D depth maps with structured light illumination. This multi-functional capability allows the same hardware to support different authentication modes, reducing overall system complexity despite enhanced security requirements.

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

Solution Approach 2:

A secure circuit acts as an intermediary that generates the pseudo-random sequence and verifies both the sequence and illumination patterns. This intermediary component coordinates the complex interactions between different capture modes, centralizing control logic and simplifying the overall system architecture.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Object-affected harmful factors

If secret illumination pattern is used, then resistance to attacks is improved, but measurement precision requirements increase

Engineering Contradiction:
Improveattack resistanceVSAvoidpattern verification accuracy
Core Design Contradiction:
Object-affected harmful factorsVSMeasurement precision

Solution Approach 1:

The illumination pattern is applied locally to specific regions of the face being captured. By focusing the structured light on the facial features and verifying the reflected pattern only in those regions, the system achieves high attack resistance while maintaining manageable verification precision requirements through localized measurement.

Inventive Principle:
Principle #3Local quality

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

This approach significantly reduces the likelihood of successful spoofing and replay attacks, ensuring that only authorized users are successfully authenticated while preventing unauthorized access.

Implementation Method 1

The sequence includes two-dimensional (with flood illumination) and three-dimensional (with depth illumination) capture modes

Methodology Applied
Scientific EffectLight emission: Light

Data Source

PatentEP3662411B1Biometric authentication techniques
Publication Date: 2024.10.09 APPLE INC
  • EP3662411B1 patent drawingFigure 1
  • EP3662411B1 patent drawingFigure 2
  • EP3662411B1 patent drawingFigure 3

AI summary

Techniques are disclosed relating to biometric authentication, e.g., facial recognition. In some embodiments, a device is configured to verify that image data from a camera unit exhibits a pseudo-random sequence of image capture modes and/or a probing pattern of illumination points (e.g., from lasers in a depth capture mode) before authenticating a user based on recognizing a face in the image data. In some embodiments, a secure circuit may control verification of the sequence and/or the probing pattern. In some embodiments, the secure circuit may verify frame numbers, signatures, and/or nonce values for captured image information. In some embodiments, a device may implement one or more lockout procedures in response to biometric authentication failures. The disclosed techniques may reduce or eliminate the effectiveness of spoofing and/or replay attacks, in some embodiments.