Image Display Authentication Using Neural Network Object Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional user authentication methods, such as PIN-based systems, can be inconvenient due to forgotten PINs, and existing AI-based systems are vulnerable to hacking attacks, necessitating a more secure and user-friendly authentication method.

Innovation Solution

An image display apparatus that uses a neural network to recognize objects from viewed content, generating an authentication image set including true and false images, allowing users to authenticate by selecting recognized images, and employs adversarial examples to enhance security against AI-based hacking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If PIN-based authentication is used, then security is provided, but user convenience deteriorates due to forgotten PINs

Engineering Contradiction:

Improveauthentication securityVSAvoiduser convenience

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system uses the user's own viewed content as the authentication basis, eliminating the need for separate memorization. The user simply selects images from content they have already watched, making the authentication process intuitive and convenient while maintaining security through unique content recognition.

Inventive Principle:

Principle #25Self-service

2Ease of operation

If AI-based authentication is implemented, then user convenience is improved, but security deteriorates due to vulnerability to hacking attacks

Engineering Contradiction:

Improveuser convenienceVSAvoidauthentication security

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system employs adversarial examples - previously hacked images - as false images in the authentication set. By converting the harmful hacking attempts into beneficial security measures, the system trains the AI to recognize and reject adversarial patterns while maintaining user-friendly operation.

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Solution Approach 2:

The authentication system combines multiple elements: true images from viewed content, false images from unviewed content, and adversarial examples from hacking attempts. This composite approach creates a robust authentication mechanism that is both convenient and secure against various attack vectors.

Inventive Principle:

Principle #40Composite materials

3Ease of operation

If object recognition from viewed content is used for authentication, then user convenience is improved, but device complexity increases due to neural network processing

Engineering Contradiction:

Improveauthentication convenienceVSAvoidsystem complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system performs object recognition and image extraction during the content viewing process itself, before authentication is needed. This preliminary processing stores extracted images ready for authentication, eliminating the need for complex real-time processing during the authentication moment and reducing perceived system complexity.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11514150B2Video display device and operating method therefor

Publication Date: 2022.11.29 SAMSUNG ELECTRONICS CO LTD

AI summary

Provided is an artificial intelligence (AI) system simulating functions of a human brain, such as recognition and decision, by using a machine learning algorithm, such as deep-learning.Image display apparatuses are more convenient for a user, by performing user authentication by using an authentication image set generated based on an object recognized from content viewed by the user.