Connected Vehicle Fleet Anomaly Detection for Cyber-Threat Mitigation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Connected vehicle fleets are vulnerable to cyber-attacks due to communication vulnerabilities, which can lead to significant harm, including vehicular accidents and financial loss, as infiltrating one vehicle can compromise the entire fleet.

Innovation Solution

A method and system that generate a fleet behavioral profile using machine learning to detect anomalies in communications among connected vehicles, allowing for real-time identification of potential threats and triggering mitigation actions such as limiting communications or sending notifications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If connected vehicles communicate with each other and centralized systems to enable fleet coordination and services, then fleet management capability and service quality are improved, but vulnerability to cyber-attacks increases

Engineering Contradiction:

Improvefleet management capabilityVSAvoidcyber-attack vulnerability

Core Design Contradiction:

Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary actions by continuously monitoring communications and training machine learning models to detect anomalies before they can cause harm. The behavioral profiles are established in advance, enabling the system to identify and respond to potential cyber-attacks before they compromise fleet security or cause accidents.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring fleet communications, comparing actual behavior against learned behavioral profiles, and automatically responding to detected anomalies. This closed-loop feedback enables real-time detection and mitigation of cyber-threats while maintaining normal fleet operations.

Inventive Principle:

Principle #23Feedback

2Measurement precision

If machine learning models are trained on fleet communication data to detect anomalies, then detection accuracy is improved, but data processing time and computational complexity increase

Engineering Contradiction:

Improveanomaly detection accuracyVSAvoiddata processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary action by training machine learning models offline on historical fleet communication data to create behavioral profiles before deployment. This pre-training approach allows the models to be ready for real-time anomaly detection without requiring extensive processing time during actual fleet operations, thus maintaining both accuracy and responsiveness.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11840244B2System and method for detecting behavioral anomalies among fleets of connected vehicles

Publication Date: 2023.12.12 UPSTREAM SECURITY LTD

AI summary

A system and method for detecting behavioral anomalies among a fleet including a plurality of connected vehicles. The method includes generating at least one fleet behavioral profile for the fleet using a first set of data, wherein creating each fleet behavioral profile includes training a machine learning model using at least a portion of the first set of data, wherein the at least a portion of the first set of data relates to communications with and among the plurality of connected vehicles; applying the at least one fleet behavioral profile to detect at least one anomaly in a second set of data for the fleet wherein the second set of data includes data related to communications with and among the plurality of connected vehicles; and performing at least one mitigation action when the at least one anomaly is detected.