Fingerprint Authentication Anti-Spoofing via Liveness Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fingerprint authentication systems face challenges in effectively rejecting spoofing attempts, as conventional methods may fail to detect presentation attacks, especially when a high-quality spoof is used and moved between authentication attempts.
Innovation Solution
The method evaluates a qualification metric based on changes in liveness scores and match scores between successive authentication attempts, incorporating factors like candidate finger probe movement and time between attempts, using an empirical model to identify patterns indicative of spoofing, and stores anti-spoofing representations to enhance recognition and rejection of subsequent attempts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional template matching is used for fingerprint authentication, then authentication speed and simplicity are improved, but the system becomes vulnerable to presentation attacks using high-quality spoofs
Solution Approach 1:
The system performs preliminary analysis of the fingerprint image to generate a qualification metric before completing the authentication decision. This preliminary action identifies potential spoofing attempts by analyzing characteristics like ridge continuity, minutiae point validity, and image quality metrics, allowing the system to reject spoofing attempts even when they pass initial template matching thresholds
Solution Approach 2:
The system incorporates feedback mechanisms by continuously monitoring authentication attempts and updating the qualification metric based on observed patterns. When a spoofing attempt is detected through analysis of fingerprint characteristics and authentication behavior patterns, the system provides feedback to reject the authentication, dynamically adjusting the security threshold based on the specific characteristics of each authentication attempt
2Reliability
If anti-spoofing measures are added to the fingerprint sensing system, then security against spoofing attempts is improved, but the device complexity increases
Solution Approach 1:
The fingerprint sensing device is designed to perform multiple functions using a unified approach. The same sensor and processing unit that capture and analyze fingerprint images for authentication also simultaneously evaluate anti-spoofing characteristics. The qualification metric integrates multiple analysis functions (image quality assessment, ridge continuity checking, minutiae validation, and pattern recognition) into a single comprehensive evaluation mechanism, avoiding the need for separate dedicated anti-spoofing hardware
3Reliability
If the system analyzes changes in liveness scores between authentication attempts, then detection of presentation attacks is improved, but the processing time increases
Solution Approach 1:
The system applies partial analysis by focusing computational resources on the most critical aspects of fingerprint authentication that are most indicative of spoofing attempts. Rather than performing exhaustive analysis of all possible fingerprint characteristics, the system prioritizes evaluation of key features such as ridge continuity, minutiae point validity, and overall image quality metrics that provide the highest discrimination power between real fingers and spoofs, achieving effective security with reduced processing overhead
Data Source
Figure 1a~1b
Figure 2
Figure 3
AI summary
A method of authenticating a user by means of a fingerprint authentication system comprising a finger sensing arrangement (3), comprising the following steps for each authentication attempt in a sequence of authentication attempts: receiving a touch by a candidate finger probe on the finger sensing arrangement; acquiring(100)a candidate fingerprint image of the candidate finger probe;determining(102) an authentication representation based on the candidate fingerprint image; retrieving(104)a stored enrollment representation of anenrolled fingerprint of theuser; determining (108)a match score based on a comparison between the authentication representation and theenrolment representation;determining a liveness score for the authentication attempt; determining(110) a qualification metric for the authentication attempt based on arelation between theliveness score for the authentication attemptand a liveness score for at least one previous authentication attempt; and determining an authentication result for the authentication attempt based on the match score, and the qualification metric.