Neural Network Detection of Unreported Cyber Events
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to accurately detect unreported cyber events experienced by entities, leading to potential risks and uncertainties for businesses relying on the cyber health of their partners or suppliers, as these entities may not truthfully report cyber incidents.
Innovation Solution
A computer-implemented method using a neural network trained on historical cyber health data of multiple entities, transforming this data into images, and utilizing technical indicators to predict and monitor reported and unreported cyber events, enabling real-time detection and assessment of cyber health.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If entities self-report cyber events, then reporting simplicity is improved, but measurement precision deteriorates due to potential false reporting or omission
Solution Approach 1:
The patent introduces technical indicators as intermediary measurements that objectively reflect an entity's cyber health status. These indicators serve as mediators between the entity's actual cyber security state and the assessment of cyber events, replacing direct self-reporting with measurable technical metrics that can be independently verified and analyzed.
Solution Approach 2:
The patent replaces the manual self-reporting mechanism with an automated technical indicator-based assessment system. Instead of relying on entities to manually report cyber events (mechanical process), the system uses technical indicators and analysis methods to automatically detect and assess cyber events, reducing human intervention and potential bias.
2Measurement precision
If comprehensive cyber security monitoring is implemented, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent segments the complex task of cyber health assessment into multiple distinct technical indicators, each measuring a specific aspect of cyber security (e.g., security controls, vulnerability management, incident response). This segmentation allows the overall assessment to be built from manageable, independent components, reducing system complexity while maintaining comprehensive coverage.
Solution Approach 2:
The patent transforms cyber health assessment from a single-dimension self-reporting approach to a multi-dimensional technical indicator framework. By adding multiple dimensions of measurement (different technical indicators covering various cyber security aspects), the system achieves more precise and comprehensive assessment without proportionally increasing complexity.
Data Source
AI summary
A computer-implemented method for detection of unreported cyber events experienced by an entity of interest is provided. The method includes instructions including obtaining training data related to estimating historical cyber health of a plurality of entities, training a neural network on the training data to create a trained neural network, and utilizing the trained neural network to generate a predicted number of cyber events experienced by the entity of interest during a time period. The instructions further include monitoring a reported number of cyber events experienced by the entity of interest during the period and generating a predicted unreported number of cyber events experienced by the entity of interest during the period based upon comparing the predicted number of cyber events experienced by the entity of interest during the period to the reported number of cyber events experienced by the entity of interest during the period.