Security Gesture Authentication for Biometric Spoofing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric authentication methods, such as facial recognition, are vulnerable to spoofing by photographs or videos, posing a significant security risk, especially in Self-Service Terminals like ATMs, leading to potential monetary losses.
Innovation Solution
Implementing a security gesture authentication system that combines facial recognition with user-defined gestures, using multiple biometric factors including background and image authentication, to enhance security and prevent spoofing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If facial recognition authentication is used, then authentication speed and ease of operation are improved, but security reliability deteriorates due to vulnerability to photograph and video spoofing
Solution Approach 1:
The authentication process is segmented into multiple independent verification stages: initial facial recognition authentication followed by a second gesture-based authentication. This segmentation ensures that even if one method is compromised, the other remains intact to prevent unauthorized access.
Solution Approach 2:
The system transitions from two-dimensional static facial image recognition to three-dimensional dynamic gesture recognition. By requiring users to perform specific hand gestures captured through depth-sensing technology, the system adds a spatial dimension that photographs and videos cannot replicate.
2Ease of operation
If traditional biometric authentication is used, then ease of operation is improved, but security against spoofing deteriorates
Solution Approach 1:
The system performs preliminary authentication through facial recognition before requiring the second gesture-based verification. This preliminary action establishes a baseline security level while maintaining user convenience, and only triggers additional verification when needed.
Solution Approach 2:
The gesture recognition system acts as an intermediary layer between the user and the authenticated resource. Rather than directly accepting facial images, the system requires an additional gesture-mediated verification step that photographs and videos cannot perform.
3Reliability
If multiple authentication factors are required, then security reliability is improved, but device complexity and authentication time increase
Solution Approach 1:
The authentication system is designed to perform multiple functions through integrated processing: facial recognition, gesture detection, and authentication decision-making are all handled within a unified system architecture, reducing overall complexity despite the multi-factor approach.
Solution Approach 2:
The system maintains continuous authentication monitoring throughout the user interaction. Rather than discrete separate steps, the authentication process flows continuously from facial recognition through gesture verification, minimizing interruptions and reducing perceived complexity for the user.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
Real-time facial recognition is augmented with an additional second biometric-based security gesture authentication. Facial biometric authentication is performed on a user for access to a resource. When facial authentication is successful, an image or a video of the user is captured performing a security gesture. Pixel values from the image or video are compared against expected pixel values for the security gesture and when the comparison is within a threshold, the user is provided access to the resource.