Intrusion detection in internet of things using differential privacy: A hybrid machine learning approach

Abstract

With the rising integration of the Internet of Things (IoT) into our daily lives, ensuring the security and privacy of these interconnected systems has become paramount. Traditional cybersecurity approaches often fall short in addressing the dual challenges of protecting IoT systems from intrusions while preserving user privacy, particularly given the complexity of IoT data and increased concerns about data privacy. Therefore, a Machine Learning (ML) based model is implemented in the proposed system to accurately classify intrusions, tailored for IoT security. In this context, this paper proposes a hybrid machine learning model: Average Orthogonal Probabilistic Random Forest-Extreme Gradient Boosting (AOPRF-XGBoost) to classify the presence and absence of intrusions in the datasets while considering different data privacy budgets. The AOPRF-XGBoost model makes use of a proposed enhanced version of Random Forest: Average Orthogonal Probabilistic Random Forest and Extreme Gradient Boosting models. A key aspect of this work is the incorporation of differential privacy mechanisms to safeguard sensitive data during model training. Differential Privacy Datasets are created by adding Gaussian noise to the existing datasets: AFDA-IDS and UNR-IDD for the AOPRF-XGBoost model, ensuring privacy protection. The experimental results of the AOPRF-XGBoost model show that the model’s accuracy improves by 3% and 1% in AFDA-IDS dataset and UNR-IDD dataset respectively, over state-of-the-art existing machine learning models, achieving a balance between Security and Privacy.