The modeling of an efficient classifier is a fundamental issue in automatic training involving a large volume of representative data. Hence, automatic classification is a major task that entails the use of training methods capable of assigning classes to data objects by using the input activities presented to learn classes. The recognition of new elements is possible based on predefined classes. Intrusion detection systems suffer from numerous vulnerabilities during analysis and classification of data activities. To overcome this problem, new analysis methods should be derived so as to implement a relevant system to monitor circulated traffic. The main objective of this study is to model and validate a heterogeneous traffic classifier capable of categorizing collected events within networks. The new model is based on a proposed machine learning algorithm that comprises an input layer, a hidden layer, and an output layer. A reliable training algorithm is proposed to optimize the weights, and a recognition algorithm is used to validate the model. Preprocessing is applied to the collected traffic prior to the analysis step. This work aims to describe the mathematical validation of a new machine learning classifier for heterogeneous traffic and anomaly detection.

Internet of Things (IoT) refers to a vast network that provides an interconnection between various objects and intelligent devices. The three important components of IoT are sensing, processing, and transmission of data. Nowadays, the new IoT technology is used in many different sectors, including the domestic, healthcare, telecommunications, environment, industry, construction, water management, and energy. IoT technology, involving the usage of embedded devices, differs from computers, laptops, and mobile devices. Due to exchanging personal data generated by sensors and the possibility of combining both real and virtual worlds, security is becoming crucial for IoT systems. Furthermore, IoT requires lightweight encryption techniques. Therefore, the goal of this paper is to identify the security challenges and key issues that are likely to arise in the IoT environment in order to guide authentication techniques to achieve a secure IoT service.

Due to the development of cloud computing and Internet of Things (IoT) environments, such as healthcare systems, telecommunications and Industry 4.0 or Industrial IoT (IIoT) many daily services are transformed. Therefore, Security issues become useful to better protect these novel technologies. IIoT security represents a real challenge for industry actors and academic research. A set of security approaches, such as intrusion detection are integrated to improve IIoT environments security. Hence, an Intrusion Detection System (IDS) aims to monitor, detect an intrusion in real time and then make reliable decisions. Many recent IDS incorporate Machine Learning (ML) techniques to improve their Accuracy (ACC), precision and Detection Rate (DR). This paper presents a hybrid IDS for Edge-Based IIoT Security using ML techniques. This new hybrid framework is based on misuse and anomaly detection using K-Nearest Neighbor (K-NN) and Principal Component Analysis (PCA) techniques. Specifically, the K-NN classifier has been incorporated to improve detection accuracy and make effective decision and the PCA is used for an enhanced feature engineering and training process. The obtained results have proven that our proposed Framework presents many advantages compared with other recent models. It gives good results with 99.10% ACC, 98.4% DR 2.7% False Alarm Rate (FAR) on NSL-KDD dataset and 98.2% ACC, 97.6% DR, 2.9% FAR on Bot-IoT dataset.

Due to the recent advancements in the Internet of things (IoT) and cloud computing technologies and growing number of devices connected to the Internet, the security and privacy issues are important to be resolved and protect the data and computer network. To provide security, a real-time monitoring of the network data and resources is needed. Intrusion detection systems have been used to monitor, detect, and alert an intrusion event in real time. Recently, the intrusion detection systems (IDS) incorporate several machine learning (ML) techniques. One of the techniques is decision tree, which can take reliable network measures and make good decisions by increasing the detection rate and accuracy. In this paper, we propose a reliable network intrusion detection approach using decision tree with enhanced data quality. Specifically, network data preprocessing and entropy decision feature selection is carried out for enhancing the data quality and relevant training; then, a decision tree classifier is built for reliable intrusion detection. Experimental study on two datasets shows that the proposed model can reach robust results. Actually, our model achieves 99.42% and 98.80% accuracy with NSL-KDD and CICIDS2017 datasets, respectively. The novel approach gives many advantages compared to the other models in term of accuracy (ACC), detection rate (DR), and false alarm rate (FAR).

Abstract-Nowadays, the protection and the security of data transited within computer networks represent a real challenge for developers of computer applications and network administrators. The Intrusion Detection System and Intrusion Prevention System are the reliable techniques for a Good security. Any detected intrusion is based on data collection. So, the collection of an important and significant traffic on the monitored systems is an interesting feature. Thus, the first task of Intrusion Detection System and Intrusion Prevention System is to collect information's basis to treat and analyze them, and to make accurate decisions. Network analysis can be used to improve networks performances and their security, but it can also be used for malicious tasks. Our main goal in this article is to design a reliable and powerful network sniffer, called PcapSockS, based on pcap language and sockets, able to intercept traffic in three modes: connected, connectionless and raw mode. We start with the performances assessment performed on a list of most expanded and most recently used network sniffers. The study will be completed by a classification of these sniffers related to computer security objectives based on parameters library (libpcap/winpcap or libnet), filtering, availability, software or hardware, alert and real time. The PcapSockS provides a nice performance integrating reliable sniffing mechanisms that allow a supervision taking into account some low and high-level protocols for TCP and UDP network communications.