Anomaly Detection in the Internet of Vehicular Networks Using Explainable Neural Networks (xNN)

Abstract

It is increasingly difficult to identify complex cyberattacks in a wide range of industries, such as the Internet of Vehicles (IoV). The IoV is a network of vehicles that consists of sensors, actuators, network layers, and communication systems between vehicles. Communication plays an important role as an essential part of the IoV. Vehicles in a network share and deliver information based on several protocols. Due to wireless communication between vehicles, the whole network can be sensitive towards cyber-attacks.In these attacks, sensitive information can be shared with a malicious network or a bogus user, resulting in malicious attacks on the IoV. For the last few years, detecting attacks in the IoV has been a challenging task. It is becoming increasingly difficult for traditional Intrusion Detection Systems (IDS) to detect these newer, more sophisticated attacks, which employ unusual patterns. Attackers disguise themselves as typical users to evade detection. These problems can be solved using deep learning. Many machine-learning and deep-learning (DL) models have been implemented to detect malicious attacks; however, feature selection remains a core issue. Through the use of training empirical data, DL independently defines intrusion features. We built a DL-based intrusion model that focuses on Denial of Service (DoS) assaults in particular. We used K-Means clustering for feature scoring and ranking. After extracting the best features for anomaly detection, we applied a novel model, i.e., an Explainable Neural Network (xNN), to classify attacks in the CICIDS2019 dataset and UNSW-NB15 dataset separately. The model performed well regarding the precision, recall, F1 score, and accuracy. Comparatively, it can be seen that our proposed model xNN performed well after the feature-scoring technique. In dataset 1 (UNSW-NB15), xNN performed well, with the highest accuracy of 99.7%, while CNN scored 87%, LSTM scored 90%, and the Deep Neural Network (DNN) scored 92%. xNN achieved the highest accuracy of 99.3% while classifying attacks in the second dataset (CICIDS2019); the Convolutional Neural Network (CNN) achieved 87%, Long Short-Term Memory (LSTM) achieved 89%, and the DNN achieved 82%. The suggested solution outperformed the existing systems in terms of the detection and classification accuracy.

A Review on the Evaluation of Feature Selection Using Machine Learning for Cyber-Attack Detection in Smart Grid

“…Additionally, the smart grid's unique ability to communicate with itself provides advantages in terms of effective energy utilization and distribution for a variety of smart devices and machines [29][30][31][32] . However, because the smart grid may store sensitive information, cybersecurity is crucial, and a variety of security solutions must be evaluated and analyzed [33][34][35] . Although the smart grid uses communication and information technology to generate, distribute, and consume electricity, there are potential disadvantages such as compromised reliability during power outages and potential privacy concerns if critical data is lost or stolen [36,37] .…”

Single and Mixed Sensory Anomaly Detection in Connected and Automated Vehicle Sensor Networks

“…The agent also has a Bayesian inference module that updates its beliefs about the environment based on new observations. The author of [22] proposed an explainable AI (XAI)-based neural network to detect real-time anomalies while explaining its decisions. The paper describes the implementation of the proposed approach using an autoencoder-based neural network that learns to reconstruct normal traffic patterns and detect anomalies based on reconstruction errors.…”

“…In summary (See Table 1), some studies exist [5,7,14,22], but they lack to provide promising performance and early detection of anomalies in automated vehicles. Therefore, we proposed this study to detect anomalies efficiently in the early stages.…”

“…[21] 2022 Introduces an approach combining deep reinforcement learning and Bayesian inference for real-time anomaly detection in dynamic environments. [22] 2022 Proposes an explainable AI (XAI)-based neural network for real-time anomaly detection in vehicular network traffic, providing explanations for its decisions.…”

Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research

“…To identify malicious DoS assaults, numerous machine learning and deep learning models have been deployed. Additionally, for the goal of model transparency, XAI methods that investigate how features contribute to or impact an algorithm-based choice can be helpful [224]. Boryau et al [225] introduced CSTITool, a CICFlowMeter-based flow extraction to feature extraction to enhance the performance of the Machine Learning DoS attack detection model.…”