ML-Based Network Port Isolation for Real-Time Threat Containment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network security systems struggle to effectively identify and isolate network ports under threat in real-time, leading to potential security breaches and network disruptions.
Innovation Solution
A machine learning (ML) based system that monitors data traffic across network ports, identifies security threats through trained ML models, and isolates potentially compromised ports, rerouting traffic to redundant ports to maintain network integrity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional network security systems are used to monitor and identify security threats, then the system structure is simple and easy to implement, but the threat detection accuracy is low and real-time identification capability is insufficient
Solution Approach 1:
The patent replaces traditional mechanical rule-based security systems with machine learning-based intelligent detection systems. The ML subsystem analyzes data traffic patterns to identify security threats, substituting manual security configuration and rule-based detection with automated learning models that continuously improve detection accuracy without requiring complex manual rule updates
Solution Approach 2:
The patent introduces an intermediate ML subsystem between the data traffic and the security response mechanism. This ML subsystem processes raw data traffic, identifies patterns indicating security threats, and triggers isolation only when threats are detected, serving as an intelligent mediator that improves detection accuracy while maintaining manageable system complexity through modular architecture
2Reliability
If network ports are isolated to prevent security threats, then the security reliability is improved, but the network operation continuity is disrupted
Solution Approach 1:
The patent implements dynamic port isolation based on real-time threat detection. Network ports are not permanently isolated but are dynamically isolated only when the ML subsystem detects security threats in their data traffic patterns. When threats are no longer detected, ports are automatically reconnected, allowing the system to maintain security reliability while minimizing disruption to network operation continuity
Solution Approach 2:
The patent establishes a feedback mechanism where the ML subsystem continuously monitors data traffic patterns of isolated ports after isolation. If the monitored patterns indicate that threats have been eliminated, the system automatically reconnects the port to the network. This feedback-driven approach ensures security reliability is maintained while restoring network operation continuity when safe to do so
Data Source
AI summary
Systems, computer program products, and methods are described herein for machine learning (ML) based network resilience and steering. An example system monitors data traffic across one or more network ports and determines a first data traffic pattern from the data traffic. The system further determines, via a ML subsystem, that the first data traffic pattern is indicative of a security threat to a first network port. In response to determining that the first data traffic pattern is indicative of the security threat to the first network port, the system further isolates the first network port from the one or more network ports.