DLIIoT: A Deep Learning based Intelligent Attack Detection in IoT Networks using Cooja Simulator
DOI:
https://doi.org/10.3329/jsr.v17i1.74612Abstract
Internet of things (IoT) has incredibly transformed the whole domain of communication process. The extensive dependency on these devices leads to various advanced cyber security threats. IoT devices fall easily into the ambit of malicious threats and are susceptible to vast range of attacks due to their limited computation capabilities and memory constraints. Intrusion Detection Systems (IDSs) are dedicated outstanding frameworks to protect these devices from cyber threats. In this study, a comprehensive review of different AI based IDS applied on IoTs is done. It has been observed that machine learning and deep learning has widely influenced the domain of IoT security. The focus of the research carried out is to earmark the techniques that are performing best on a given data set. Features selection, type of attacks, proposed solutions in solving security menaces are taken into consideration. Further, we have presented DLIIoT, a deep learning based intelligent attack detection in IoT networks by generating precise IoT datasets in Cooja Simulator. Four Deep learning algorithms are utilized and analysed under standard performance criteria metrics such as Precision, Recall, Accuracy and F1-score. It was found that deep learning algorithms have remarkable potential in detecting and recognizing malicious data patterns in IoT networks.
Downloads
717
155
Downloads
Published
How to Cite
Issue
Section
License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
© Journal of Scientific Research
Articles published in the "Journal of Scientific Research" are Open Access articles under a Creative Commons Attribution-ShareAlike 4.0 International license (CC BY-SA 4.0). This license permits use, distribution and reproduction in any medium, provided the original work is properly cited and initial publication in this journal. In addition to that, users must provide a link to the license, indicate if changes are made and distribute using the same license as original if the original content has been remixed, transformed or built upon.