Neural-Network Authentication for Anti-Forgery Device Verification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing authentication methods for electronic devices are inadequate in ensuring secure and reliable communication between devices, particularly against malicious access attempts.

Innovation Solution

Implementing neural networks for authentication processes, including features like recognizing data features, classifying data, extracting hidden data, and generating random data, to enhance security and reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional authentication methods are used, then the authentication process is simple and fast, but the security and reliability are insufficient against malicious devices

Engineering Contradiction:
Improveauthentication securityVSAvoidauthentication process complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces neural networks as an intermediary component between the authentication challenge and response verification. The neural network processes authentication data through learned patterns, acting as a mediator that enhances security without requiring complete redesign of the authentication protocol. This allows traditional authentication frameworks to leverage AI-based security improvements.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent transforms authentication verification from deterministic parameter matching to probabilistic pattern recognition. By changing the verification parameter from exact match to neural network confidence thresholds, the system achieves higher security while maintaining acceptable processing speeds. The neural network learns to recognize legitimate authentication patterns versus malicious attempts through training data.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If neural networks are implemented for authentication, then security and reliability are enhanced, but the processing time and computational resources increase

Engineering Contradiction:
Improveauthentication securityVSAvoidauthentication processing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent performs neural network training and model optimization in advance, before actual authentication occurs. Authentication challenges are preprocessed and filtered through multiple stages, with the neural network ready with pre-learned patterns. This preliminary preparation significantly reduces real-time processing requirements during actual authentication events.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The authentication process is divided into distinct stages: challenge generation, neural network inference, response verification, and decision making. The neural network component is isolated as a separate processing module, allowing optimization of each stage independently. This segmentation enables parallel processing and reduces overall authentication latency.

Inventive Principle:
Principle #1Segmentation

3Reliability

If neural networks are used to recognize data features and generate random data, then authentication becomes more difficult to forge, but the device complexity and energy consumption increase

Engineering Contradiction:
Improveauthentication anti-forgery capabilityVSAvoiddevice energy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent replaces traditional cryptographic mechanical systems with neural network-based pattern recognition. Instead of relying solely on mathematical encryption, the system uses learned representations of authentication data that are more difficult to forge. The neural network substitutes for traditional key management and cryptographic verification mechanisms.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The neural network performs self-verification by comparing authentication responses against learned patterns without requiring external reference data. The model learns to recognize legitimate devices through training and then autonomously verifies future authentication attempts, reducing the need for continuous external validation and lowering operational energy requirements.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4672049A1Authentication method
Publication Date: 2025.12.31 STMICROELECTRONICS INT NV
  • EP4672049A1 patent drawingFigure 1
  • EP4672049A1 patent drawingFigure 2
  • EP4672049A1 patent drawingFigure 3

AI summary

This description relates to a method for authenticating a first device (P) with a second device (V), comprising the following successive steps: - Sending, by said second device (V), to said first device (P), at least one first piece of data (Chall200); - Using, by said first device (P), a first neural network to provide a second piece of data (Rsp200) from said at least one first piece of data (Chall200); - Sending, by said first device, said second piece of data (Rsp200) to said second device (V).