Face Authentication PPG Liveness Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Face authentication on mobile devices is vulnerable to photo-based forgery attacks (PFA) and video-based forgery attacks (VFA), as existing defenses rely on liveness detection methods that are either ineffective or require additional sensors not available in commercially available devices, such as infrared cameras or advanced motion analysis.
Innovation Solution
A system that uses photoplethysmography (PPG) by recording videos of a user's face and fingertip simultaneously with a mobile device's cameras, comparing the consistency of the PPGs to verify the authenticity of the user, leveraging the dynamic nature of cardiac activity to distinguish real-time video from forged content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If liveness detection methods using infrared cameras or advanced motion analysis are used, then security against PFA and VFA is improved, but device complexity and cost increase due to requiring additional sensors
Solution Approach 1:
The patent applies multi-functionality by using the existing camera and light source for dual purposes: standard imaging and photoplethysmography-based liveness detection. The camera captures both visual information and subtle skin color variations caused by blood flow, while the light source serves both illumination and PPG signal generation functions. This eliminates the need for dedicated infrared cameras or additional sensors, resolving the contradiction between security improvement and device complexity.
Solution Approach 2:
The system uses the mobile device's own existing components (camera, light source, processor) to perform liveness detection without requiring external or additional hardware. The camera that is already present in the device is made to serve the additional function of detecting photoplethysmographic signals from the user's face, allowing the device to authenticate liveness using its self-contained resources rather than additional sensors.
2Reliability
If photoplethysmography-based liveness detection is implemented, then security against PFA and VFA is improved, but the system complexity increases due to requiring simultaneous multi-camera coordination and PPG comparison
Solution Approach 1:
The system segments the liveness detection process into distinct functional modules: (1) simultaneous video capture from multiple cameras, (2) PPG signal extraction from facial video, (3) PPG signal extraction from fingertip video, (4) consistency comparison between PPGs, and (5) authentication decision. This modular segmentation manages system complexity by organizing the sophisticated multi-camera PPG comparison process into manageable, independent processing stages that can be implemented and maintained separately.
3Reliability
If photoplethysmography-based liveness detection is implemented, then security against PFA and VFA is improved, but processing time increases due to requiring simultaneous video recording and PPG comparison
Solution Approach 1:
The system performs preliminary action by continuously capturing and pre-processing video frames in real-time as the user interacts with the device. The cameras continuously record video, and the system pre-extracts PPG signals from the video stream before authentication is actually required. This preliminary processing ensures that when authentication is needed, the PPG comparison can be performed quickly using already-prepared data, reducing the actual authentication time while maintaining security.
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
The system effectively defends against PFA and VFA with high true positive rates and low false negative rates, achieving robust security for face authentication on mobile devices without requiring additional sensors, as confirmed by extensive user experiments.
Implementation Method 1
The camera is operated to record changes in skin color caused by blood flow to thereby obtain a PPG
Data Source
AI summary
A system for authenticating a user attempting to access a computing device or a software application executing thereon. A data storage device stores one or more digital images or frames of video of face(s) of authorized user(s) of the device. The system subsequently receives from a first video camera one or more digital images or frames of video of a face of the user attempting to access the device and compares the image of the face of the user attempting to access the device with the stored image of the face of the authorized user of the device. To ensure the received video of the face of the user attempting to access the device is a real-time video of that user, and not a forgery, the system further receives a first photoplethysmogram (PPG) obtained from a first body part (e.g., a face) of the user attempting to access the device, receives a second PPG obtained from a second body part (e.g., a fingertip) of the user attempting to access the device, and compares the first PPG with the second PPG. The system authenticates the user attempting to access the device based on a successful comparison of (e.g., correlation between, consistency of) the first PPG and the second PPG and based on a successful comparison of the image of the face of the user attempting to access the device with the stored image of the face of the authorized user of the device.