IoT based intrusion detection data analysis using deep learning models

Abstrak

In both the academic and industrial domains, integration of the internet of things (IoT) is now universally accepted as a significant technical achievement. IoT offers a multitude of security issues despite its many advantages, such as protecting networks and devices, handling resourceconstrained network scenarios, and controlling threats to IoT networks. This article gives a state-of-the-art analysis on the application of multiple deep learning (DL) algorithms in IoT intrusion detection systems (IDS), covering the years 2020 to 2024. Moreover, two popular network datasets, NSL-KDD and UNSW-NB15, are used for an experimental evaluation. The study thoroughly examines and assesses the advantages of well-known deep learning algorithms, including DNN, CNN, RNN, LSTM, and FFDNN. The study demonstrates the exceptional performance of the DNN approach on both datasets, with 99.14% accuracy in multiclass classification in NSLKDD and 99.36% accuracy in binary classification. Furthermore, on UNSWNB15, 82.26% of multiclass classifications and 93.96% of binary classifications with a 42-second minimum running time were achieved, along with an excellent performance in reducing false alarms at a rate of 2.19%.