An Accurate Detection Approach for IoT Botnet Attacks Using Interpolation Reasoning Method

Abstract

Nowadays, the rapid growth of technology delivers many new concepts and notations that aim to increase the efficiency and comfort of human life. One of these techniques is the Internet of Things (IoT). The IoT has been used to achieve efficient operation management, cost-effective operations, better business opportunities, etc. However, there are many challenges facing implementing an IoT smart environment. The most critical challenge is protecting the IoT smart environment from different attacks. The IoT Botnet attacks are considered a serious challenge. The danger of this attack lies in that it could be used for several threatening commands. Therefore, the Botnet attacks could be implemented to perform the DDoS attacks, phishing attacks, spamming, and other attack scenarios. This paper has introduced a detection approach against the IoT Botnet attacks using the interpolation reasoning method. The suggested detection approach was implemented using the interpolation reasoning method instead of the classical reasoning methods to handle the knowledge base issues and reduce the size of the detection fuzzy rules. The suggested detection approach was designed, tested, and evaluated using an open-source benchmark IoT Botnet attacks dataset. The implemented experiments show that the suggested detection approach was able to detect the IoT Botnet attacks effectively with a 96.4% detection rate. Furthermore, the obtained results were compared with other literature results; the accomplished comparison showed that the suggested method is a rivalry with other methods, and it effectively reduced the false positive rate and interpolated the IoT Botnet attacks alerts even in case of a sparse rule base.

Botnet Attack Detection in IoT Devices using Ensemble Classifiers with Reduced Feature Space

“…Alissa et al (2022) [35] decision tree, XgBoost, and logistic regression performed with 94% accuracy. The authors of [36] utilized LSTM and CNN to give 94% accuracy and Multi-CNN gave 96% accuracy. In [37] we have made a comparative analysis for full datasets and reduced datasets (using principal component analysis) and found 7 better performed machine learning algorithms and those identified best performing algorithms were used in this work.…”

Systematic Literature Review of IoT Botnet DDOS Attacks and Evaluation of Detection Techniques

“…Model-based testing and policy-based management 2020 [113] Mirai traffic signatures 2022 [115] Interpolation reasoning 2022 [116] Firewall rules Neisse et al proposed in 2017 an integrated approach to enhance the certification process of IoT devices using Model-Based Testing and policy-based management [114]. The approach includes security functional testing using Model-Based Testing (MBT) with TTCN3, model-based policy specification and enforcement using the SecKit toolkit, and post-certification monitoring to detect vulnerabilities and enforce policies dynamically.…”

“…Almseidin et al [ 115 ] propose a detection approach for IoT botnet attacks using the interpolation reasoning method. The approach involves investigating network traffic to extract relevant network parameters, applying the resampling technique, checking for missing observations, searching for input parameters, eliminating other network parameters, and storing the top three input parameters for training and optimization.…”

A novel hybrid feature selection and ensemble-based machine learning approach for botnet detection

“…The FPR of this research is 0.02, which is higher for a large dataset. A brand-new IRM-based botnet detection technique was introduced in 2022 by Almseidin et al 15 for the detection of IoT botnets. They used the method in an ambiguous environment and achieved accuracy of about 96%.…”