Bifurcated ML Attack Characterization for Real-Time Vulnerability Assessment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems fail to provide accurate, real-time, and user-friendly indications of security vulnerabilities in computing platforms, leading to potential data breaches and inefficient resource usage due to outdated and unreliable security information.

Innovation Solution

A system that utilizes bifurcated machine learning-based processing of multi-modal data to predict cyber-security attack characteristics and determine computing aspect impact levels, providing a graphical user interface for clear security vulnerability assessments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual techniques are employed to determine security vulnerabilities, then network engineers can assess system security, but the process is time-consuming and prone to errors due to subjective opinions

Engineering Contradiction:

Improvesecurity vulnerability assessment accuracyVSAvoidtime to publish security information

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical assessment processes with automated machine learning models that process multi-modal data (logs, metrics, traces) to objectively determine security vulnerabilities, eliminating human subjectivity and accelerating the assessment process from days to real-time

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service security assessment by automatically collecting, processing, and analyzing security data without requiring manual intervention from network engineers, who only need to review pre-generated vulnerability determinations and recommendations

Inventive Principle:

Principle #25Self-service

2Reliability

If network engineers rely on publicly available security information, then they can make security decisions, but the information is outdated and filled with inaccuracies

Engineering Contradiction:

Improvesecurity information accuracyVSAvoidreal-time vulnerability data

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The system performs preliminary security assessments by continuously collecting and analyzing security data before attacks occur, maintaining up-to-date vulnerability information that reflects the current system state rather than relying on outdated public reports

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback loops where the machine learning model continuously receives new security data, adjusts its vulnerability assessments, and provides real-time updates to network engineers, ensuring information remains current and accurate

Inventive Principle:

Principle #23Feedback

3Reliability

If attackers exploit newly discovered vulnerabilities in real-time, then security breaches occur, but network engineers cannot respond quickly enough due to delays in vulnerability publication

Engineering Contradiction:

Improvesystem securityVSAvoidresponse time to vulnerabilities

Core Design Contradiction:

ReliabilityVSSpeed

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements continuous security monitoring and assessment processes that operate without interruption, ensuring real-time detection and response to vulnerabilities rather than periodic manual reviews

Inventive Principle:

Principle #20Continuity of useful action

4Productivity

If a large amount of time and resources are devoted to correcting security vulnerabilities, then more vulnerabilities can be addressed, but network engineers disagree on which vulnerabilities to correct first

Engineering Contradiction:

Improvevulnerability correction throughputVSAvoidvulnerability prioritization process

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The patent replaces subjective human judgment in vulnerability prioritization with machine learning models that objectively analyze impact data and automatically rank vulnerabilities by severity, eliminating disagreements and enabling efficient resource allocation

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12608486B2Generating predicted end-to-end cyber-security attack characteristics via bifurcated machine learning-based processing of multi-modal data systems and methods

Publication Date: 2026.04.21 CITIBANK N A

AI summary

Systems and methods for generating predicted end-to-end cyber-security attack characteristics via bifurcated machine learning-based processing of multi-modal data are disclosed. The system accesses multi-modal data indicating a set of security information related to a computing system. The system then generates a set of extracted characteristics indicating a cyber-security attack on the computing system, via a supervised machine learning model, using the multi-modal data. Using this information, the system generates a revised set of extracted characteristics indicating the cyber-security attack, via an unsupervised machine learning model, using the extracted set of characteristics indicating the cyber-security attack, where the revised set of characteristics includes at least one new characteristic that was not included in the extracted set of characteristics indicating the cyber-security attack on the computing system. The system then generates for display a graphical representation of the revised set of extracted characteristics.