Deep Learning Models for Cyber Security in IoT Networks

By Monika Roopak, Gui Yun Tian, Jonathon A. Chambers. Computing and Communication Workshop and Conference, 2019

318 citations recorded by the source corpus.

In this paper we propose deep learning models for the cyber security in IoT (Internet of Things) networks. IoT network is as a promising technology which connects the living and non-living things around the world. The implementation of IoT is growing fast but the cyber security is still a loophole, so it is susceptible to many cyber-attack and for the success of any network it most important that the network is completely secure, otherwise people could be reluctant to use this technology. DDoS (Distributed Denial of Service) attack has affected many IoT networks in recent past that has resulted in huge losses. We have proposed deep learning models and evaluated those using latest CICIDS2017 datasets for DDoS attack detection which has provided highest accuracy as 97.16% also proposed models are compared with machine learning algorithms. This paper also identifies open research challenges for usage of deep learning algorithm for IoT cyber security.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

View Paper: https://www.semanticscholar.org/paper/43b99b798a29272a203782d19181998cd57d0fd2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Signal Processing

Citations in the corpus

Adversarial Machine Learning for Network Intrusion Detection Systems: A Comprehensive Survey (2023, methodology): “However, despite the RNN-based advances in the NLP domain, NIDS designs with RNN as the detection algorithm still use LSTM models or plain RNN for detection [41], [53], [55].”
Lucid: A Practical, Lightweight Deep Learning Solution for DDoS Attack Detection (2020, methodology): “In contrast, E3ML, DeepGFL and most of the solutions proposed in [38], which all rely on flow-level features, seem to be more prone to false negatives, and hence to classify DDoS attacks as normal activity.”
Internet of Underwater Things and Big Marine Data Analytics—A Comprehensive Survey (2020, background): “Furthermore, if a sole ML model has to detect a collection of multiple attacks, DBNs might be considered as a better choice [301], [303].”
A Review on Machine Learning and Deep Learning Perspectives of IDS for IoT: Recent Updates, Security Issues, and Challenges (2020, methodology): “DBN technique is also applied for attack classification and analysis of IoT networks [173, 174].”