Remote Liveness Detection Using Cue-Triggered User Reactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing identity verification systems face challenges in confirming the liveness of a user when identity confirmation is conducted remotely, as they are vulnerable to fraudsters submitting images or synthetically generated faces, making it difficult to distinguish between a live person and a fraudulent representation.
Innovation Solution
A method and system for detecting liveness using a client device that generates cues to induce both involuntary and voluntary user reactions, analyzing sensor data to determine if the reactions meet predefined thresholds, thereby confirming the user's presence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional identity verification methods are used, then the process is simple, but the system is vulnerable to fraudsters submitting images or synthetically generated faces
Solution Approach 1:
The verification process is segmented into multiple independent liveness detection challenges (involuntary actions and voluntary actions). Each challenge is evaluated separately, and both must be passed to confirm liveness. This segmentation allows the system to address different types of fraud attempts through specialized detection mechanisms while maintaining overall system reliability.
Solution Approach 2:
The system dynamically adapts the verification process by selecting different types of challenges (involuntary or voluntary actions) based on the detection results. If involuntary actions indicate liveness, the system proceeds to voluntary actions for further verification. This dynamic adaptation allows the system to maintain high reliability while managing complexity through conditional execution paths.
2Reliability
If multiple liveness detection challenges are implemented, then fraud detection capability improves, but the verification process time increases
Solution Approach 1:
The verification process is made dynamic by implementing conditional execution paths. The system first evaluates involuntary actions, and only if those indicate liveness does it proceed to voluntary actions. This dynamic structure allows the system to reduce verification time when possible (by stopping after the first successful detection) while maintaining high fraud detection capability when needed.
Solution Approach 2:
The system uses feedback from each detection challenge to determine the next step in the verification process. The results of involuntary action detection feed back into the decision-making process, determining whether to proceed to voluntary action challenges. This feedback mechanism optimizes verification time by avoiding unnecessary challenges when liveness is already confirmed.
3Reliability
If involuntary actions are used for liveness detection, then the ability to distinguish live users from fraudsters improves, but the system complexity increases
Solution Approach 1:
The liveness detection system is segmented into distinct modules: involuntary action detection module and voluntary action detection module. Each module handles specific types of challenges and evaluation criteria. This segmentation allows the system to achieve high reliability through specialized detection algorithms while managing complexity through modular architecture, where each module can be independently developed and tested.
Data Source
AI summary
The disclosure includes a system and method for detecting liveness including generating a first cue for presentation to a user via a client device, the first cue for inducing a first action when the user is live; receiving sensor data representing a first reaction by the user to the first cue; determining, based on the first reaction, whether the first reaction satisfies a threshold; and determining that the user is live based on a determination that the first reaction satisfies a threshold.