Cross Deep Learning Method for Effectively Detecting the Propagation of IoT Botnet

Abstract

In recent times, organisations in a variety of businesses, such as healthcare, education, and others, have been using the Internet of Things (IoT) to produce more competent and improved services. The widespread use of IoT devices makes our lives easier. On the other hand, the IoT devices that we use suffer vulnerabilities that may impact our lives. These unsafe devices accelerate and ease cybersecurity attacks, specifically when using a botnet. Moreover, restrictions on IoT device resources, such as limitations in power consumption and the central processing unit and memory, intensify this issue because they limit the security techniques that can be used to protect IoT devices. Fortunately, botnets go through different stages before they can start attacks, and they can be detected in the early stage. This research paper proposes a framework focusing on detecting an IoT botnet in the early stage. An empirical experiment was conducted to investigate the behaviour of the early stage of the botnet, and then a baseline machine learning model was implemented for early detection. Furthermore, the authors developed an effective detection method, namely, Cross CNN_LSTM, to detect the IoT botnet based on using fusion deep learning models of a convolutional neural network (CNN) and long short-term memory (LSTM). According to the conducted experiments, the results show that the suggested model is accurate and outperforms some of the state-of-the-art methods, and it achieves 99.7 accuracy. Finally, the authors developed a kill chain model to prevent IoT botnet attacks in the early stage.

MalBoT-DRL: Malware Botnet Detection Using Deep Reinforcement Learning in IoT Networks

“…The early stages of the malware life cycle were examined through an experiment conducted using the MedBIoT dataset. The results, generated using SOTA ML [61], [62], DL [41], [45], [61] , and DRL [70]models, indicate that these models exhibit good performance in detecting malware activities, with the exception of a few ML models. Related performance metrics are detailed in Table X and Fig.…”

“…However, this approach neglects low-traffic DDoS attacks. Wazzan et al [41]have employed a different architecture as compared to Alghazzawi et al [40] to investigate the propagation stages of malware botnets and their communication with the C&C. Their proposed approach yielded promising results, achieving an accuracy rate of 99.7%. However, the authors have used a simulated dataset for their evaluation, which may differ from real-world scenarios.…”

“…In this study, the performance of the proposed MalBoT-DRL model is compared with two other models, namely Parallel Learning [45] and CNN-LSTM [41], in terms of their resource requirements and processing times during both training and testing phases using psutil library [99]. The comparison is illustrated in Fig.…”

An Anomaly Intrusion Detection for High-Density Internet of Things Wireless Communication Network Based Deep Learning Algorithms

“…This growth will be reflected in the fact that scientists consider the number of IoT interconnections to reach 83 billion by the year 2024 [ 1 ]. Since these electronics are connected to the internet and accessible around the clock, it is simple to obtain accurate data in a timely manner [ 2 , 3 ]. As a result, the proliferation of wireless telecommunication infrastructures, wireless handheld devices (such as mobiles), and wireless communication networks has made it possible to organize massive amounts of data at once.…”