Developing an Intelligent System for Efficient Botnet Detection in IoT Environment
Smart technological instruments and Internet of Things (IoT) systems are now targeted by network attacks because of their widespread rising use. Attackers can take over IoT devices via botnets, and pre-configured attack vectors, and use them to do harmful actions. Thus, effective machine learning is...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ram Arti Publishers
2025-04-01
|
| Series: | International Journal of Mathematical, Engineering and Management Sciences |
| Subjects: | |
| Online Access: | https://www.ijmems.in/cms/storage/app/public/uploads/volumes/27-IJMEMS-24-0684-10-2-537-553-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Smart technological instruments and Internet of Things (IoT) systems are now targeted by network attacks because of their widespread rising use. Attackers can take over IoT devices via botnets, and pre-configured attack vectors, and use them to do harmful actions. Thus, effective machine learning is required to solve these security issues. Additionally, deep learning with the necessary elements is advised to defend the network from these threats. In order to achieve proper detection of hacks in the future, relevant datasets must be used. The device's operation could occasionally be delayed. The sample dataset must be well structured for training the model and validating the suggested model to create the best protection system model feasible for detecting cyber risks. This paper focused on analyzing botnet traffic in an IoT environment using machine learning and deep learning classifiers: Decision tree classifier, Naïve Bayes, K nearest neighbor, Convolution neural network, Recurrent neural network, and Random Forest. We calculated each algorithm's Accuracy, True Positive, False Positive, False Negative, True Negative, Precision, and Recall. We obtained impressive results using these CNN, and LSTM RNN classifiers. We have also achieved a high attack detection rate. |
|---|---|
| ISSN: | 2455-7749 |