EIDM: deep learning model for IoT intrusion detection systems
Elnakib, O; Shaaban, E; Mahmoud, M; Karim Emara;
Abstract
Internet of Things (IoT) is a disruptive technology for the future decades. Due to its pervasive growth, it is susceptible to cyber-attacks, and hence the significance of Intrusion Detection Systems (IDSs) for IoT is pertinent. The viability of machine learning has encouraged analysts to apply learning techniques to intelligently discover and recognize cyber attacks and unusual behavior among the IoTs. This paper proposes an enhanced anomaly-based Intrusion Detection Deep learning Multi-class classification model (EIDM) that can classify 15 traffic behaviors including 14 attack types with the accuracy of 95% contained in the CICIDS2017 dataset. Four state-of-the-art deep learning models are also customized to classify six classes of network traffic behavior. An extensive comparative study in terms of classification accuracy and efficiency metrics is conducted between EIDM and several state-of-the-art deep learning-based IDSs showing that EIDM has achieved accurate detection results.
Other data
Title | EIDM: deep learning model for IoT intrusion detection systems | Authors | Elnakib, O; Shaaban, E; Mahmoud, M; Karim Emara | Keywords | IoT;Cyber security;Deep learning;Intrusion detection;Supervised learning;ATTACK DETECTION;INTERNET;CHALLENGES | Issue Date | Mar-2023 | Publisher | SPRINGER | Journal | Journal of Supercomputing | ISSN | 0920-8542 | DOI | 10.1007/s11227-023-05197-0 | Scopus ID | 2-s2.0-85150694912 | Web of science ID | WOS:000957533900002 |
Recommend this item
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.