Towards a Universal Features Set for IoT Botnet Attacks Detection

Abstract

The security pitfalls of IoT devices make it easy for the attackers to exploit the IoT devices and make them a part of a botnet. Once hundreds of thousands of IoT devices are compromised and become the part of a botnet, the attackers use this botnet to launch the large and complex distributed denial of service (DDoS) attacks which take down the target websites or services and make them unable to respond the legitimate users. So far, many botnet detection techniques have been proposed but their performance is limited to a specific dataset on which they are trained. This is because the features used to train a machine learning model on one botnet dataset, do not perform well on other datasets due to the diversity of attack patterns. Therefore, in this paper, we propose a universal features set to better detect the botnet attacks regardless of the underlying dataset. The proposed features set manifest preeminent results for detecting the botnet attacks when tested the trained machine learning models over three different botnet attack datasets.

Artificial Intelligence for anomaly detection by employing deep learning strategies in IoT networks using the trendy IoT-23 big data from Google's Tensorflow2.2

“…IoT-23 dataset as a component of the Avast Software subsidizing AIC research facility, which is available from the website "https://www.stratosphereips.org/datasets-iot23", is an IoT network dataset of 8.8 GB that carries 20 malware subsets and 3 benign subsets ['Label', 'Cat', 'Sub_Cat'] [7]. The dataset turned into the rst of all made to be had in January 2020 through the Stratosphere Laboratory in Czechia [8].…”

“…Keeping in mind, the following top 10 features are extracted by using logistic regression in this referred article, which is used in this building model [12]. Binary Classi cation of the feature 'Label': Three target feature classi cations are there, 'Label', 'Cat', 'Sub_Cat'.…”

“…So the total number of features in consideration is 79 features. 7. Building The Model Of The Supervised Deep Learning Algorithms 7.1.…”

A Framework for Malicious Traffic Detection in IoT Healthcare Environment

“…Furthermore, it is estimated that by 2025 there will be 75.44 billion IoT connected worldwide [ 1 ]. IoT footprints have been identified in various domains such as manufacturing, agriculture, transportation, electric grid, healthcare, among others [ 2 , 3 , 4 ]. In an IoT-based healthcare system, security is the primary concern as the data is directly related to human beings.…”

“…Therefore, it is very challenging to design a security mechanism for IoT devices. The manufacturing industries are producing a massive amount of IoT products to create low-cost IoT devices in a short period [ 3 , 18 ]. Due to the race to the market for capturing the market as earlier as possible, the manufacturers are giving less importance to the device security [ 3 ].…”