Faulty Control Detection Using Incident-Code Embeddings

Solution Overview

Problem

Existing systems fail to effectively identify and modify faulty controls in computing systems, leading to difficulties in preventing incidents such as cybersecurity incidents, as they struggle to determine which controls are related to an incident and require significant resources to train machine learning models for identifying faulty controls.

Innovation Solution

The use of machine learning to map incident data and control data to the same vector space, allowing for the identification of problematic code and generation of recommendations for modifications, along with a weighting mechanism to improve the quality and efficiency of training data for machine learning models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If machine learning models are trained to identify faulty controls, then detection accuracy is improved, but training time and computational resources increase

Engineering Contradiction:

Improvedetection accuracyVSAvoidtraining time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing control code into embeddings and pre-training the machine learning model on historical control data before actual fault detection is needed. This allows the model to be ready for rapid deployment without requiring training at the moment of detection, thus improving detection accuracy while managing training time through advance preparation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates embeddings as simplified copies or representations of the original control code. These embeddings capture the essential features of controls in a compressed format that is more efficient for machine learning processing, allowing accurate fault detection without requiring the model to process the full complexity of original control code, thereby reducing computational resources and training time.

Inventive Principle:

Principle #26Copying

2Measurement precision

If machine learning models are trained to identify faulty controls, then detection accuracy is improved, but computational resources required increase

Engineering Contradiction:

Improvedetection accuracyVSAvoidcomputational resources

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system creates embeddings as simplified copies or representations of the original control code. These embeddings capture the essential features of controls in a compressed format that is more efficient for machine learning processing, allowing accurate fault detection without requiring the model to process the full complexity of original control code, thereby reducing computational resources and training time.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system transforms control code from its original complex form into embeddings with different parameters - simplified numerical representations that preserve essential characteristics. This parameter transformation reduces the dimensionality and complexity of the data, enabling the machine learning model to achieve high detection accuracy with reduced computational resources and energy consumption.

Inventive Principle:

Principle #35Parameter changes

3Reliability

If existing systems attempt to identify which controls are related to incidents, then incident prevention capability is improved, but system complexity increases

Engineering Contradiction:

Improveincident prevention capabilityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system introduces embeddings as an intermediary layer between the original control code and the machine learning model. These embeddings serve as a mediator that simplifies the relationship between controls and incidents, allowing the model to identify faulty controls without directly analyzing the full complexity of control code and incident data, thus improving incident prevention capability while managing system complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates embeddings as simplified copies or representations of the original control code. These embeddings capture the essential features of controls in a compressed format that is more efficient for machine learning processing, allowing accurate fault detection without requiring the model to process the full complexity of original control code, thereby reducing computational resources and training time.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20240168473A1Machine learning for detecting and modifying faulty controls

Publication Date: 2024.05.23 CAPITAL ONE SERVICES LLC

AI summary

In some aspects, a computing system may use machine learning to determine whether a control is faulty or generate recommendations to make a modification to a control. may identify a portion of problematic computer code that implements the faulty control through the use of machine learning. A computing system may use machine learning to generate embeddings that map incident data and control data (e.g., computer-readable code of a control) to the same vector space. Further, a computing system may use a weighting mechanism that may be used to weight each sample used to train a machine learning model, which may allow a model to train more efficiently.