Search

The Vehicular Ad Hoc Network (VANET) is a novel and innovative technology which is part of the Intelligent Transportation Systems (ITS). VANET is a network composed of a collection of vehicles and other roadside components that are interconnected wirelessly. The intention underlying the development of this technology is the improvement of the vehicle environment and the enhancement of vehicle and driver safety. Nevertheless, since VANETs operate wirelessly and under complicated conditions, they are susceptible to a variety of attacks by malicious actors. Traditional techniques such as encryption are no longer effective, so new techniques using intrusion detection systems IDS have attracted the attention of a large number of researchers. The IDS scans the entire network and identifies all the possible harmful nodes present in the network. The present paper covers the problem of the identification of attacks in VANET by using XGBoost. The effectiveness analysis of the proposed models has been realized on the NSL-KDD and 5RoutingMetrics datasets combined with various feature selection techniques Boruta and Adaptive Synthetic Sampling Approach (ADASYN). Furthermore, the acquired results are being compared to two of the last most used ensemble methods CatBoost and convolutional neural networks CNN.In comparison with the other IDSs, our model approach achieves high performance in accuracy, recall and precision. [ABSTRACT FROM AUTHOR]

Internet of Things (IoTs) has been playing an important role in many sectors, such as smart cities, smart agriculture, smart healthcare, and smart manufacturing. However, IoT devices are highly vulnerable to cyber-attacks, which may result in security breaches and data leakages. To effectively prevent these attacks, a variety of machine learning-based network intrusion detection methods for IoT networks have been developed, which often rely on either feature extraction or feature selection techniques for reducing the dimension of input data before being fed into machine learning models. This aims to make the detection complexity low enough for real-time operations, which is particularly vital in any intrusion detection systems. This paper provides a comprehensive comparison between these two feature reduction methods of intrusion detection in terms of various performance metrics, namely, precision rate, recall rate, detection accuracy, as well as runtime complexity, in the presence of the modern UNSW-NB15 dataset as well as both binary and multiclass classification. For example, in general, the feature selection method not only provides better detection performance but also lower training and inference time compared to its feature extraction counterpart, especially when the number of reduced features K increases. However, the feature extraction method is much more reliable than its selection counterpart, particularly when K is very small, such as K = 4 . Additionally, feature extraction is less sensitive to changing the number of reduced features K than feature selection, and this holds true for both binary and multiclass classifications. Based on this comparison, we provide a useful guideline for selecting a suitable intrusion detection type for each specific scenario, as detailed in Table 14 at the end of Sect. 4. Note that such the comparison between feature selection and feature extraction over UNSW-NB15 as well as theoretical guideline have been overlooked in the literature. [ABSTRACT FROM AUTHOR]

Software-defined networking (SDN) is a new network paradigm, which is highly decoupled compared to traditional networks, and makes it easier to operate by separating the data and control planes of the network, promoting logical centralization of network control, and introducing the ability to program the network. Due to the feature of logically centralized control, the attack on the controller will lead to the paralysis of the entire network, so the intrusion detection is particularly important for SDN. With the rise of artificial intelligence network, machine learning technology and deep learning technology have been applied in all aspects of life. Due to the advantages of high accuracy, light weight, and fast response speed, deep learning is beneficial for intrusion detection. However, the methods proposed at this stage are mainly concentrated in traditional networks, and they are often used to detect DDoS (Distributed Denial of Service) attacks only, which cannot be applied to SDN directly to classify different attack types specific to this new network paradiam. In this work, we propose a hybrid Long Short Term Memory (LSTM)-based multi-class intrusion detection method, i.e., Convolutional Neural Network with Attention (CNNA)-BiLSTM to detect 8 common intrusion types on the InSDN dataset. Firstly, a feature selection method is proposed for the high-dimensional data of SDN network data traffic to extract the positive features that are effective for model decision-making, reduce the misleading of the model by unfavorable and negative features, and decrease the computational cost. Secondly, a multi-class intrusion detection model based on multi-output nodes and hybrid BiLSTM with attention is proposed to improve the accuracy of the model for emerging detection. The proposed deep learning model provides a better classification result in two-class and multi-class problems compared with other methods. It achieves an accuracy of 99.86% and 99.31% on two-class and multi-class scenarios, respectively. Moreover, our proposed model can accurately detect each category in multi-classification detection, while other standard models cannot detect Botnet, Web, and U2R attacks accurately because of their small sample scales. [ABSTRACT FROM AUTHOR]

The number of cloud-, edge-, and Internet of Things (IoT)-based applications that produce sensitive and personal data has rapidly increased in recent years. The IoT is a new model that integrates physical objects and the Internet and has become one of the principal technological evolutions of computing. Cloud computing is a paradigm for centralized computing that gathers resources in one place and makes them available to consumers via the Internet. Despite the vast array of resources that cloud computing offers, real-time mobile applications might not find it acceptable because it is typically located far from users. However, in applications where low latency and high dependability are required, edge computing—which disperses resources to the network edge—is becoming more and more popular. Though it has less processing power than traditional cloud computing, edge computing offers resources in a decentralized way that can react to customers' needs more quickly. There has been a sharp increase in attackers stealing data from these applications since the data is so sensitive. Thus, a powerful Intrusion Detection System (IDS) that can identify intruders is required. IDS are essential for the cybersecurity of the IoT, cloud, and edge architectures. Investigators have mostly embraced the use of deep learning algorithms as a means of protecting the IoT environment. However, these techniques have some issues with computational complexity, long processing times, and poor precision. Feature selection approaches can be utilized to overcome these problems. Optimization methods, including bio-inspired algorithms, are applied as feature selection approaches to enhance the classification accuracy of IDS systems. Based on the cited sources, it appears that no study has looked into these difficulties in depth. This research thoroughly analyzes the current literature on intrusion detection and using nature-inspired algorithms to safeguard IoT and cloud/edge settings. This article examines pertinent analyses and surveys on the aforementioned subjects, dangers, and outlooks. It also examines many frequently used algorithms in the development of IDSs used in IoT security. The findings demonstrate their efficiency in addressing IoT and cloud/edge ecosystem security issues. Moreover, it has been shown that the methods put out in the literature might improve IDS security and dependability in terms of precision and execution speed. [ABSTRACT FROM AUTHOR]

Utilizing the cloud environment is one of the most preferable option in every information technology (IT) organization for running its business due to its flexible nature of services for its users. Cloud computing is vulnerable to various types of known and unknown attacks due to its distributed nature and open architecture. Hence, privacy and security is a primary concern of the cloud computing environment. A lot of machine learning approaches are utilized to improve the accuracy of Intrusion detection system (IDS) but dealing with redundant and non-relevant datasets with a large number of attributes (multi-dimensional) is still a problem. In this study, better and fast IDS has been proposed to detect anomaly for the cloud network environment which uses Improved squirrel search algorithm (ISSA) and Modified-deep belief network (MDBN) on the UNSW-NB15 dataset. ISSA extracts the relevant features from a set of features to deal with network traffic data of high dimension. It selects the relevant and optimal feature subset to be utilized for the training process and testing process. Meanwhile, a MDBN is introduced which uses the extracted features for anomaly detection for binary class classification and multi class classification. MDBN also helps to deal with the unbalanced nature of the dataset. The proposed IDS model has been evaluated based on the statistical measures namely accuracy, false alarm rate (FAR) and execution time, which are the popular parameters for evaluation of an IDS model. The proposed ISSA-MDBN model for IDS reduces the training from 103.51 to 0.108 s and testing time from 29.62 to 0.054 s on the UNSW-NB15 dataset. The proposed IDS model has been compared with other existing recent approaches and the proposed approach achieves the highest accuracy of 99.8% and lowest FAR of 0.02%. [ABSTRACT FROM AUTHOR]