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.
In this paper, we present an Intrusion Detection System (IDS) using the hybridization of the deep learning technique and the multi-objective optimization method for the detection of Distributed Denial of Service (DDoS) attacks in the Internet of Things (IoT) networks is proposed in this paper. IoT networks consist of different devices with unique hardware and software configurations communicating over different communication protocols, which produce huge multidimensional data that make IoT networks susceptible to cyber-attacks. In a network the IDS is a vital tool for securing it from cyber-attacks. Detection of new emerging cyber threats are becoming difficult for existing IDS, and therefore advanced IDS is required. A DDoS attack is a cyber-attack that has posed substantial devastating losses in IoT networks recently. In this paper, we propose an IDS founded on the fusion of a Jumping Gene adapted NSGA-II multi-objective optimization method for data dimension reduction and the Convolutional Neural Network (CNN) integrating Long Short-Term Memory (LSTM) deep learning techniques for classifying the attack. The experimentation is conducted using a High-Performance Computer (HPC) on the latest CISIDS2017 datasets on DDoS attacks and achieved an accuracy of 99.03% with a 5-fold reduction in training time. We evaluated our proposed method by comparing it with other state-of-the-art algorithms and machine learning algorithms, which confirms that the proposed method surpasses other approaches.
In this study, the authors propose a multi‐objective optimisation‐based feature selection (FS) method for the detection of distributed denial of service (DDoS) attacks in an internet of things (IoT) network. An intrusion detection system (IDS) is one approach for the detection of cyber‐attacks. FS is required to reduce the dimensionality of data and improve the performance of the IDS. One of the reasons for the failure of an IDS is incorrect selection of features because most of the FS methods are based on a limited number of objectives such as accuracy or relevance of data, but these are not enough as they can be misleading for attack detection the contribution of this work is to develop appropriate FS method. They have implemented the nondominated sorting algorithm with its adapted jumping gene operator to solve the optimisation problem and exploited an extreme learning machine as the classifier for FS based on six important objectives for an IoT network. Experimental results verify that the proposed method performs well for FS and have achieved 99.9% and has reduced the total number of features by nearly 90%. The proposed method outperforms other proposed FS methods for the detection of DDoS attacks by an IDS.
The authors introduce an unsupervised Intrusion Detection System designed to detect zero‐day distributed denial of service (DDoS) attacks in Internet of Things (IoT) networks. This system can identify anomalies without needing prior knowledge or training on attack information. Zero‐day attacks exploit previously unknown vulnerabilities, making them hard to detect with traditional deep learning and machine learning systems that require pre‐labelled data. Labelling data is also a time‐consuming task for security experts. Therefore, unsupervised methods are necessary to detect these new threats. The authors focus on DDoS attacks, which have recently caused significant financial and service disruptions for many organisations. As IoT networks grow, these attacks become more sophisticated and harmful. The proposed approach detects zero‐day DDoS attacks by using random projection to reduce data dimensionality and an ensemble model combining K‐means, Gaussian mixture model, and one‐class SVM with a hard voting technique for classification. The method was evaluated using the CIC‐DDoS2019 dataset and achieved an accuracy of 94.55%, outperforming other state‐of‐the‐art unsupervised learning methods.
22 September 2023 in Forensic Science International: Digital Investigation