The distributed nature of Internet of Things (IoT) and its rapid increase on a large scale raises many security and privacy issues. Access control is one of the major challenges currently addressed through centralized approaches that may rely on a third party and they are constrained by availability and scalability, which may result in a performance bottleneck. Therefore, this paper proposes a novel solution to manage the delivery of lightweight and decentralized secure access control of an IoT system based on a multi-agent system and a blockchain. The main objective of the proposed solution is to build Blockchain Managers (BCMs) for securing IoT access control, as well as allowing for secure communication between local IoT devices. Moreover, the solution also enables secure communication between IoT devices, fog nodes and cloud computing.

Detecting botnet threats has been an ongoing research endeavor. Machine Learning (ML) techniques have been widely used for botnet detection with flow-based features. The prime challenges with flow-based features are that they have high computational overhead and do not fully capture network communication patterns. Recently, graph-based ML has witnessed a dramatic increase in attention. In communication networks, graph data offers insights information about communication patterns between hosts. In this paper, we propose a graph-based ML model for botnet detection that first considers the significance of graph features before developing a generalized model for detecting botnets based on the selected important features. We explore different feature sets selected using five filter-based feature evaluation measures derived from various theories such as consistency, correlation, and information. Two heterogeneous botnet datasets, CTU-13 and IoT-23, were used to evaluate the effectiveness of the proposed graph-based botnet detection with several supervised ML algorithms. Experiment results show that using features reduces training time and model complexity and provides high bots detection rate. Our proposed detection model detects different types of botnet families and exhibits robustness to zero-day attacks. Compared to state-of-the-art techniques flow-, and graph-based, our approach achieves higher precision and shows competitive accuracy.

The Internet of Medical Things are susceptible to Man-in-the-Middle (MitM) attack, which can identify healthcare emergency of monitored patients and replay normal physiological data to prevent the system from raising an alarm. In this article, we propose a framework to prevent a MitM from disrupting the operations and prohibiting the raise of alarms by the remote healthcare monitoring system. To reduce energy consumption for normal data transmission, and preserve the privacy of health data, our framework transmits a smaller size signature derived from acquired data with message authentication code, where the key is derived from received signal strength indication. Our experimental results for emergency detection show that our approach can achieve a high detection accuracy with a low false alarm rate of 3%.

In recent decades, the internet has grown and changed the world tremendously, and this, in turn, has brought about many cyberattacks. Cybersecurity represents one of the most serious threats to society, and it costs millions of dollars each year. The most significant question remains: Where do these attacks come from? The answer is that botnets provide platforms for cyberattacks. For many organizations, a botnet-assisted attack is a terrifying threat that can cause financial losses and leave global victims in its wake. It is therefore imperative to defend organizations against botnet-assisted attacks. Software defined networking (SDN) has emerged as one of the most promising paradigms for this because it allows exponential increases in the complexity of network management and configuration. SDN has a substantial advantage over traditional approaches with regard to network management because it separates the control plane from network equipment. However, security challenges continue to arise, which raises the need for different types of implementation strategies to spread attack vectors, despite the significant benefits. The main objective of this survey is to assess botnet detection techniques by using systematic reviews and meta-analyses (PRISMA) guidelines. We evaluated various articles published since 2006 in the field of botnet detection, based on machine learning, and from 2015 in the field of SDN. Specifically, we used top-rated journals that featured the highest impact factors. In this paper, we aim to elaborate on several research areas regarding botnet attacks, detection techniques, machine learning, and SDN. We also address current research challenges and propose directions for future research.

In this article, a new procedure is proposed on the basis of Hilbert-Huang Transform and deep learning for cyber-attacks detection in direct current (DC) micro-grids (MGs) as well as detection of the attacks in distributed generation (DG) units and its sensors. An advanced elective group deep learning method with Krill Herd Optimization (KHO) algorithm is proposed. At first, Hilbert-Huang Transform is used with the aim of extracting the signals feature and next these features are applied as the multiple deep input basis models are made with the aim of capturing automatically sentient traits from raw fluctuation signals. At third, to make sure the variety of the basis patterns, linear decoder, denoising autoencoder and sparse autoencoder are applied to make various deep autoencoders, respectively. Further, Bootstrap is applied with the aim of designing separate educational data subsets for any base model. Fourth, for implementing selective ensemble learning, a combination strategy of enhanced weighted voting (EWV) with class-particular thresholds is studied. Eventually, KHO algorithm is applied with the aim of adaptive selecting the optimal class-specific thresholds. In the offered tactic, firstly, a DC micro-grid is functioned and controlled with the lack of any false data injection attacks (FDIAs) to collect adequate information within the usual operation needed for the educating of deep learning networks. It is noteworthy that, in the procedure of datum production, load variable is also determined with the aim of having distinctive datasets for cyber-attack scenarios and load variables. Also, to provide more realistic method, the smart plug-in electric vehicle is also considered in the model. Outcomes of Simulation in various scenarios are applied with the aim of verifying the benefit of the offered procedure. The outcomes propose that the offered procedure is able to more accurate and robust know various type of false data injection attack over than 93.76% accuracy detection of true rate.