Treffer: An AI-Based Cyber Ranges to Strengthen the Cybersecurity of Cyber Physical Systems.

This research demonstrates that integrating artificial intelligence into cyber range platforms significantly enhances cybersecurity readiness for cyber-physical systems by improving threat detection accuracy, accelerating incident response, and enabling adaptive learning. We developed a hybrid AI-powered cyber range architecture combining cloud-based simulation for scalability with emulation-based components for physical system fidelity. The framework leverages LSTM and GRU networks trained on 2.6 billion security events and implemented using Python 3.9 with Keras/TensorFlow, optimized via Adam optimizer (90.0% accuracy vs. 85.9% for ADAMAX). Results revealed three critical advancements: 91.3% classification accuracy in detecting coordinated attacks, identification of 76/107 security vulnerabilities (71% success rate) with 89.47% concept recognition, and a 34% reduction in detection-to-mitigation time compared to conventional cyber ranges. While demonstrating superior performance in controlled environments (90.9% accuracy in patch validation), challenges persist in AI explainability—only 58% of cybersecurity professionals could interpret model decisions, underscoring the need for interpretable machine learning frameworks in operational deployments. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Applied Security Research is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)