Multi-Factor Facial Image Authentication for Fraud Prevention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing authentication methods for ATMs and electronic devices are vulnerable to fraud, particularly facial recognition systems that can be tricked by two-dimensional representations of authorized users, leading to potential unauthorized access.
Innovation Solution
Implementing a multi-factor facial image authentication system that captures a first facial image and compares it with stored credentials, followed by a second facial image captured after displaying a facial gesture cue, ensuring that both match associated credentials, and optionally using a secondary biometric sensor for additional security.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If facial recognition authentication is used, then authentication speed and convenience are improved, but vulnerability to spoofing attacks increases
Solution Approach 1:
The patent transforms static facial recognition into dynamic authentication by requiring users to perform specific facial gestures (e.g., opening mouth, raising eyebrows, turning head) in response to system prompts. This dynamic component prevents spoofing with static photographs while maintaining user convenience through simple gesture execution.
Solution Approach 2:
The patent adds temporal and behavioral dimensions to facial authentication. Instead of only spatial facial features, the system captures facial movements over time and analyzes gesture sequences, transforming a 2D static problem into a 4D dynamic verification process that includes time and motion vectors.
2Reliability
If multi-factor authentication is implemented, then authentication security is improved, but system complexity increases
Solution Approach 1:
The patent merges multiple authentication factors into a unified facial gesture verification process. Instead of separate steps for card insertion, PIN entry, and facial recognition, the system combines these into an integrated workflow where facial gestures serve as the primary and potentially sole authentication mechanism, reducing operational complexity.
Solution Approach 2:
The system uses the user's own facial features and movements as the authentication credential, eliminating the need for external tokens, cards, or passwords. The user's face and gestures become the self-contained authentication key, simplifying the system architecture while maintaining high security.
3Productivity
If static facial images are used for authentication, then authentication speed is improved, but susceptibility to fraud increases
Solution Approach 1:
The patent implements periodic authentication challenges where the system issues sequential gesture prompts (first gesture, then second gesture) during the authentication process. This periodic verification rhythm maintains fast authentication while ensuring the user is actively participating rather than presenting a pre-recorded image.
Solution Approach 2:
The system dynamically changes authentication parameters by selecting from multiple possible facial gestures and sequences. Instead of verifying a single static facial configuration, the system varies the required gestures (mouth open, eyes closed, head rotation) to create unique authentication instances that prevent replay attacks while maintaining consistent verification speed.
Data Source
AI summary
A method and system for authenticating users accessing financial accounts from user terminals via multi-factor image authentication. The system includes an authentication server and a user terminal. The method captures a first facial image of a user and compares this image with stored facial recognition credentials. The method prompts the user via a facial gesture cue to make a facial gesture, captures a second facial image of the user, and compares the second image with stored facial gesture credentials. The user is authorized to perform a transaction in the event the first facial image matches a facial recognition credential for an authorized account, and the second facial image matches a facial gesture credential associated with the authorized account. Facial gesture credentials may be based upon static gestures or dynamic gestures, and may be overt or secret. An additional authentication factor may employ a secondary biometric sensor.