Adaptive Reference Enrollment for Low-False-Alarm Authentication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing security systems face challenges in accurately distinguishing between genuine security breaches and false alarms, and in adapting to changes in user characteristics over time for effective authentication and access control.
Innovation Solution
A security system utilizing machine learning and deep learning algorithms to analyze image and audio information, determining a relatedness metric for authentication, and triggering validation requests when uncertainty is detected, with features like facial recognition and acoustic analysis to enhance user authentication and access control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If motion-based event generation is used to detect security breaches, then security monitoring capability is improved, but false alarm rate increases
Solution Approach 1:
The system uses feedback loops where authentication results and validation outcomes continuously refine the reference information. The processor compares candidate information against reference information, and when validation succeeds, the reference information is updated. This feedback mechanism allows the system to learn from past decisions and improve its ability to distinguish genuine security breaches from false alarms over time.
Solution Approach 2:
The system dynamically adjusts parameters such as the relatedness metric threshold and validation criteria based on accumulated data. By changing the parameters of comparison and validation processes, the system can adapt to different security contexts and reduce false alarms while maintaining detection capability.
2Measurement precision
If reference information is updated frequently to adapt to user changes, then authentication accuracy is improved, but system complexity increases
Solution Approach 1:
The system performs self-updating of reference information through automated validation processes. When candidate information is received and compared against reference information, the system automatically determines whether to update the reference information based on validation success, without requiring manual intervention. This self-service approach maintains authentication accuracy while managing system complexity through automation.
Solution Approach 2:
The system updates reference information selectively rather than continuously - only when validation succeeds. This partial action approach maintains authentication accuracy by updating only when necessary, while avoiding the complexity of continuous monitoring and updating mechanisms.
3Reliability
If validation requests are triggered for uncertain cases, then authentication reliability is improved, but processing time increases
Solution Approach 1:
The system applies validation requests selectively only to cases where the relatedness metric falls below a threshold or uncertainty is detected. For clear-cut cases with high confidence, the system proceeds directly without validation. This partial action approach maintains authentication reliability for uncertain cases while minimizing processing time delays.
Solution Approach 2:
Different processing approaches are applied to different cases based on their characteristics. High-confidence cases receive rapid processing, while uncertain cases undergo additional validation. This local quality approach ensures reliability where needed while maintaining overall processing efficiency.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Person or object authentication can be performed using artificial intelligence-enabled systems. Reference information, such as for use in comparisons or assessments for authentication, can be updated over time to accommodate changes in an individual's appearance, voice, or behavior. In an example, reference information can be updated automatically with test data, or reference information can be updated conditionally, based on instructions from a system administrator. Various types of media can be used for authentication, including image information, audio information, or biometric information. In an example, authentication can be performed wholly or partially at an edge device such as a security panel in an installed security system.