Automated Network Perimeter Definition via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining a network perimeter for organizations are often incomplete or outdated, requiring significant technical expertise and frequent updates, which can lead to ineffective network security policies and vulnerabilities to unauthorized access.
Innovation Solution
A system that automatically determines a network perimeter by analyzing connection data from client devices using a machine learning-based model, which receives input on network zones and outputs security scores to recommend an ideal network perimeter, with continuous adjustment based on new connection data and administrator feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If network administrators manually define network perimeter using network zones, then network security policies can be implemented, but significant technical expertise is required and the information becomes outdated frequently
Solution Approach 1:
The system automatically determines network perimeter by analyzing connection data from client devices without requiring manual intervention from network administrators. The automated system service monitors connection requests, identifies trusted network zones, and maintains perimeter definitions autonomously, eliminating the need for administrators to manually define and update network zones while ensuring continuous accuracy
Solution Approach 2:
The patent replaces the manual mechanical process of administrators defining network perimeters with an automated computational system that analyzes connection data. The system uses automated algorithms to process connection requests, identify patterns, and determine trusted network zones, substituting human expertise and manual updates with automated data-driven decision-making
2Reliability
If network administrators diligently update network perimeter information regularly, then the network perimeter remains accurate, but the process requires significant time and expertise
Solution Approach 1:
The system continuously monitors connection data from client devices in real-time, automatically updating network perimeter definitions without interruption. The automated system maintains continuous analysis of connection requests and dynamically adjusts perimeter information, ensuring constant currency without requiring periodic manual updates that consume administrator time
Solution Approach 2:
The automated system self-updates network perimeter information by continuously analyzing connection data and identifying trusted zones. The system serves itself by autonomously maintaining accurate perimeter definitions without requiring external intervention or time investment from network administrators for updates
3Ease of operation
If automated system analyzes connection data to determine network perimeter, then technical expertise requirement is reduced, but the system requires processing of large volumes of connection data
Solution Approach 1:
The system extracts only the essential and relevant features from large volumes of connection data, such as source IP addresses, connection patterns, and authentication outcomes. By extracting key indicators of trusted network zones rather than processing entire raw datasets, the system reduces the effective data volume requiring detailed analysis while maintaining accuracy in perimeter determination
Data Source
AI summary
A system generates network perimeter for an organization based on the connection data. The system builds a model, for example, a machine learning based model configured to receive a network zone as input and output a score indicating security of the network zone. The system receives information describing connection requests received from client devices associated with the organization. The system adjusts parameters of the machine learning based model based on information describing the connection requests. The adjusting of the machine learning based model improves the accuracy of prediction based on the information describing the connection requests. The system determines a network perimeter for the organization using the machine learning based model. The network perimeter may be used for implementing a network policy for the organization based on the determined network perimeter.