IEEE Access (Jan 2024)
Using IOTA Tangle and Machine Learning for a Defensive Model-Based Approach Against Replication Attacks on Wireless Sensor Networks
Abstract
Wireless Sensor Networks (WSNs) are essential for data collection across various domains but face growing risks from replication attacks, which introduce new vulnerabilities and security challenges. To address this issue, we propose a novel hybrid approach that integrates Distributed Ledger Technology (DLT) with adaptive Machine Learning (ML) methods, aiming to bolster both security and trustworthiness within WSNs. Specifically, our approach utilizes DLT to secure voting records and manage rewards, while adaptive ML models detect replica nodes by analyzing network parameters, including location, signal strength, and transmission rate. We present and evaluate three ML-based models for detecting replication attacks: 1) Random Forest Model (RFM), 2) Adaptive Weighted Random Forest Model based on Predicted Replica Nodes (AWRFM-PRN), and 3) Adaptive Weighted Random Forest Model based on Predicted Good and Replica Nodes (AWRFM-PGRN). The AWRFM-PRN and AWRFM-PGRN models enhance detection accuracy through iterative weight adjustments based on previous predictions. Our simulations show that the hybrid approach significantly improves detection performance compared to traditional methods. We evaluated our models by increasing the dataset size with varying proportions of replica nodes across ten subsets. We found that the AWRFM-PGRN model achieved around 71% accuracy when replica nodes comprised 50% or more of the network. Meanwhile, the AWRFM-PRN model demonstrated high effectiveness with accuracy ranging from 80% to 99% for replica nodes constituting 15% to 40% of the network. Furthermore, all models delivered nearly 99.9% accuracy when the proportion of replica nodes was between 5% and 10%. This innovative integration of DLT with adaptive ML modeling establishes a benchmark for robust and tamper-proof security in WSNs, offering significant enhancements over traditional ML techniques such as RFM, particularly in scenarios with high replica node counts.
Keywords