Object-Based User Authentication Using Scene and Sequence Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing user authentication methods, such as passwords and biometrics, are unreliable and vulnerable to compromise, necessitating a more secure and flexible authentication mechanism.
Innovation Solution
A computer-based system that registers and detects physical objects and background scenes using image data, employing machine learning to authenticate users by comparing presented objects and sequences with registered credentials.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional password or biometric authentication is used, then the authentication process is simple to implement, but the security and reliability of user permission verification deteriorates
Solution Approach 1:
The authentication system segments the verification process into multiple independent components: object detection, background scene analysis, and sequence verification. Each component processes a specific aspect of the authentication challenge, allowing the system to achieve high security through modular, manageable segments rather than a single complex verification mechanism.
Solution Approach 2:
The patent adds temporal dimension by requiring users to present physical objects in a specific sequence over time. This transforms static authentication (single moment verification) into dynamic multi-dimensional authentication that considers not only what objects are present but also the order and timing of their presentation, significantly enhancing security without requiring overly complex hardware.
2Reliability
If physical objects and background scenes are required for authentication, then the security against unauthorized access improves, but the ease of operation deteriorates
Solution Approach 1:
The system allows users to register their own physical objects and background scenes during setup, creating personalized authentication credentials that are meaningful to them. This self-service approach makes the authentication process more convenient as users can choose objects they already possess and backgrounds they are familiar with, reducing the operational burden while maintaining high security.
Solution Approach 2:
The system performs preliminary registration of physical objects and background scenes during setup, storing these credentials for future verification. This preliminary action reduces the complexity of the authentication process during actual use, as the system only needs to verify against pre-stored credentials rather than requiring complex real-time analysis, thereby improving ease of operation.
3Measurement precision
If machine learning models are used to compute authentication probability, then the accuracy of permission verification improves, but the processing time and computational resources increase
Solution Approach 1:
The system uses machine learning models to compute a probability score for authentication verification, applying partial action by setting a threshold (e.g., 70% probability) that determines sufficient verification. This approach balances accuracy and processing time by not requiring absolute certainty, allowing the system to make timely authorization decisions with high but not perfect confidence, thus reducing processing time while maintaining adequate accuracy.
Data Source
AI summary
Systems and methods of the present disclosure physical object-based passwords by registering an object password including first object representations, first background scene representations, and a first presentation sequence from first image data. Receiving second image data and a second presentation sequence that is a second order in which the user has presented second physical objects to an image acquisition device, and detecting in the second image data second object representations of the second physical objects, and second background scene representations. Computing a probability that the user is a permissioned user by inputting the first image data and the second image data into a machine learning model configured to compute the probability based on comparing the object password and the second image data. Tagging the user as the permissioned user or non-permissioned user based on the probability.