Threat analysis of IoT networks using artificial neural network intrusion detection system

Hodo, Elike; Bellekens, Xavier; Hamilton, Andrew; Dubouilh, Pierre-Louis; Iorkyase, Ephraim; Tachtatzis, Christos; Atkinson, Robert

doi:10.1109/isncc.2016.7746067

Cited by 399 publications

(184 citation statements)

References 9 publications

Supporting

Mentioning

174

Contrasting

Unclassified

Order By: Relevance

“… Artificial Neural Network (ANN) Intrusion Detection System: Here a multi-level perceptron, a type of supervised ANN, is trained using internet packet traces and was assessed on its ability to thwart Distributed Denial of Service (DDoS/DoS) attacks on IoT devices [20].The detection was based on classifying normal and threat patterns. It was able to identify successfully different types of attacks and showed good performances in terms of true and false positive rates.…”

Section: Svelte Ids In Iot [2]mentioning

confidence: 99%

Intrusion Detection in Internet of Things (Iot)

Anthony¹,

John²,

Emmanuel³

2018

ijarcs

View full text Add to dashboard Cite

Section: Svelte Ids In Iot [2]mentioning

confidence: 99%

Intrusion Detection in Internet of Things (Iot)

Anthony¹,

John²,

Emmanuel³

2018

ijarcs

View full text Add to dashboard Cite

“…Since then, many ML and DM algorithms were specifically designed for the purpose. DM algorithms examine the valuable information within large volume of data by analytically discovering underlying major trends, patterns, and associations from the data as reported in [10,11]. Therefore, an artificial neural network (ANN) can be used to solve multiclass problems for the IDS using a classic multilayer feed-forward NN trained with a back-propagation algorithm to predict intrusions [12].…”

Section: Related Workmentioning

confidence: 99%

“…The most of the important parameter for the performance evaluation of IDS is detection rate (DR). This parameter measures the number of correctly detected attacks from a total number of attacks as defined in Equation (10). Then, the false alarm rate (FAR) measures the ratio between the numbers of normal connections that are incorrectly misclassified as attacks and a total number of normal connections defined in Equation (11).…”

Section: Kdd Cup 1999 Datasetmentioning

confidence: 99%

Network Intrusion Detection through Discriminative Feature Selection by Using Sparse Logistic Regression

et al. 2017

View full text Add to dashboard Cite

Intrusion detection system (IDS) is a well-known and effective component of network security that provides transactions upon the network systems with security and safety. Most of earlier research has addressed difficulties such as overfitting, feature redundancy, high-dimensional features and a limited number of training samples but feature selection. We approach the problem of feature selection via sparse logistic regression (SPLR). In this paper, we propose a discriminative feature selection and intrusion classification based on SPLR for IDS. The SPLR is a recently developed technique for data analysis and processing via sparse regularized optimization that selects a small subset from the original feature variables to model the data for the purpose of classification. A linear SPLR model aims to select the discriminative features from the repository of datasets and learns the coefficients of the linear classifier. Compared with the feature selection approaches, like filter (ranking) and wrapper methods that separate the feature selection and classification problems, SPLR can combine feature selection and classification into a unified framework. The experiments in this correspondence demonstrate that the proposed method has better performance than most of the well-known techniques used for intrusion detection.

show abstract

“…In the formula: X represents the data packet quantization parameter; B is the value coefficient of the packet attribute; M1 and Sd are the average coefficients and the average error coefficient corresponding to B [7][8] .…”

Section: The Technical Advantages Of the New Detection Systemmentioning

confidence: 99%

Research on network intrusion detection technology in dynamic and complex background

Zheng¹,

Liu²

2017

Proceedings of the 2017 2nd International Conference on Materials Science, Machinery and Energy Engineering (MSMEE 2017)

View full text Add to dashboard Cite

Abstract.With the advent of the Internet era, the network has been widely used in production and life, and network security has become a hot topic. Nowadays, the traditional prevention technology is difficult to prevent the various increasing network attacks. There is an urgent need for a complex network intrusion detection technology to ensure the normal use of the network. According to the above problems, this paper studies the problem of network intrusion detection technology in dynamic and complex background. This paper introduces the network intrusion detection technology under dynamic background, and expounds the basic idea of detection, detection system model and packet capture device of detection system, and then analyzes the technical advantages of the detection system. the experiment proves that the network intrusion detection system can detect intrusion quickly and accurately to prevent intrusion.

show abstract

Threat analysis of IoT networks using artificial neural network intrusion detection system

Cited by 399 publications

References 9 publications

Intrusion Detection in Internet of Things (Iot)

Intrusion Detection in Internet of Things (Iot)

Network Intrusion Detection through Discriminative Feature Selection by Using Sparse Logistic Regression

Research on network intrusion detection technology in dynamic and complex background

Contact Info

Product

Resources

About