A Data Rate Monitoring Approach for Cyberattack Detection in Digital Twin Communication.

Area of Science:

• Cybersecurity in Industrial Internet of Things (IIoT)
• Digital Twin technology
• Industry 4.0 security

Background:

• Digital Twins (DTs) in Industry 4.0 environments present significant cybersecurity risks.
• Existing security solutions are often complex and resource-intensive.
• The physical-virtual communication layer is a critical vulnerability point.

Purpose of the Study:

• To demonstrate a computationally efficient anomaly detection method for DT communications.
• To validate the effectiveness of simple statistical metrics for identifying cyber threats.
• To enhance the resilience of IIoT-based DTs against cyberattacks.

Main Methods:

• Utilized a Docker-based simulation to emulate cyberattacks.
• Simulated Denial-of-Service (DoS), Man-in-the-Middle (MiTM), and intrusion attacks.
• Applied statistical metrics, specifically the μ+3σ threshold, for anomaly detection based on data rate monitoring.

Main Results:

• Each attack type generated a distinct statistical signature.
• A 50-fold increase in packet rate was observed during DoS attacks.
• Data rate monitoring proved to be a viable anomaly detection method.

Conclusions:

• Simple statistical metrics provide robust, interpretable, and efficient anomaly detection for DT communications.
• Data rate monitoring serves as a cost-effective, non-intrusive first line of defense.
• This approach enhances the overall cybersecurity posture of IIoT-based Digital Twins.