A novel intrusion detection system based on deep learning and random forest for digital twin on IOT platform

Digital Twin (DT) has bright prospects for a broad spectrum of applications, such as supply chain, healthcare, predictive maintenance, etc. On one hand, the intrinsic properties of DT make it highly relevant to real-world applications, while on the other hand, they render it vulnerable to cyber threats. So, the security of DT is of utmost importance for the security of the communication and computational infrastructure underneath it. As cybercriminals are always coming up with new attack techniques, it is essential to safeguard the digital twin against malicious attacks. This can be accomplished by putting in place an efficient security mechanism, one of which is an intrusion detection system (IDS). The work done in this paper introduces a novel hybrid model for IDS in digital twins that integrates deep learning (DL) and random forest (RF). The effectiveness of the developed model is evaluated in comparison to that of k-Nearest Neighbors (KNN), Naive Bayes, Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Long Short Term Memory (LSTM), and it’s evident from the outcome that the proposed method has higher accuracy than the competing models by at least 5%. In addition to its high accuracy, our proposed model also promises impressively low computing time requirements when compared to other competing models.