A Novel Anomaly Detection System on the Internet of Railways Using Extended Neural Networks

Abstract

The Internet of Railways (IoR) network is made up of a variety of sensors, actuators, network layers, and communication systems that work together to build a railway system. The IoR’s success depends on effective communication. A network of railways uses a variety of protocols to share and transmit information amongst each other. Because of the widespread usage of wireless technology on trains, the entire system is susceptible to hacks. These hacks could lead to harmful behavior on the Internet of Railways if they spread sensitive data to an infected network or a fake user. For the previous few years, spotting IoR attacks has been incredibly challenging. To detect malicious intrusions, models based on machine learning and deep learning must still contend with the problem of selecting features. k-means clustering has been used for feature scoring and ranking because of this. To categorize attacks in two datasets, the Internet of Railways and the University of New South Wales, we employed a new neural network model, the extended neural network (ENN). Accuracy and precision were among the model’s strengths. According to our proposed ENN model, the feature-scoring technique performed well. The most accurate models in dataset 1 (UNSW-NB15) were based on deep neural networks (DNNs) (92.2%), long short-term memory LSTM (90.9%), and ENN (99.7%). To categorize attacks, the second dataset (IOR dataset) yielded the highest accuracy (99.3%) for ENN, followed by CNN (87%), LSTM (89%), and DNN (82.3%).

Hunting Network Anomalies in a Railway Axle Counter System

“…The papers most similar to our approach are those included in Table 1 in the cybersecurity section [ 18 , 19 , 20 , 21 ]. In these works, the authors used data from network communication protocols as data sources.…”

“…As a test environment, we had a physical test environment simulating axle counting. In papers [ 18 , 20 , 21 ], the authors, such as us, dealt with supervised learning ML methods. However, neither paper focuses on the kNN algorithm, which in our case came out best of the classical machine learning algorithms.…”

“…Our work focuses primarily on anomaly detection in the area of cybersecurity in railways. This area of anomalies has been the focus of several works in recent years [ 18 , 19 , 20 , 21 ].…”

“…Islam et al [ 20 ] primarily focused on the potential of anomaly detection cyber-attacks on the Internet of Things (IoT) in a railway environment. They presented two datasets, one focusing purely on IoT and the other on IoT in railway environments.…”

KDDT: Knowledge Distillation-Empowered Digital Twin for Anomaly Detection

“…However, such complexity renders RWS susceptible to broader threats (e.g., anomalies [2] and software faults [40]). In particular, anomalies are one of the most severe threats that might lead to system failures or even catastrophic consequences [19].…”