A Big Network Traffic Data Fusion Approach Based on Fisher and Deep Auto-Encoder

Tao, Xiaoling; Kong, Deyan; Wei, Yang; Wang, Yong

doi:10.3390/info7020020

Cited by 28 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A DAE is a feedforward neural network strategy for fast unsupervised computing execution [85]. It investigates the estimation of a unique task, where the result ðxÞ is equal to the input ðxÞ to construct a definition of a collection of data, that is, ðx ⟶ xÞ, ðxÞ.…”

Section: Deep Autoencoder (Dae)mentioning

confidence: 99%

See 1 more Smart Citation

Intrusion Detection in Industrial Internet of Things Network‐Based on Deep Learning Model with Rule‐Based Feature Selection

Awotunde

Chakraborty

Adeniyi

2021

Wireless Communications and Mobile Computing

127

View full text Add to dashboard Cite

The Industrial Internet of Things (IIoT) is a recent research area that links digital equipment and services to physical systems. The IIoT has been used to generate large quantities of data from multiple sensors, and the device has encountered several issues. The IIoT has faced various forms of cyberattacks that jeopardize its capacity to supply organizations with seamless operations. Such risks result in financial and reputational damages for businesses, as well as the theft of sensitive information. Hence, several Network Intrusion Detection Systems (NIDSs) have been developed to fight and protect IIoT systems, but the collections of information that can be used in the development of an intelligent NIDS are a difficult task; thus, there are serious challenges in detecting existing and new attacks. Therefore, the study provides a deep learning-based intrusion detection paradigm for IIoT with hybrid rule-based feature selection to train and verify information captured from TCP/IP packets. The training process was implemented using a hybrid rule-based feature selection and deep feedforward neural network model. The proposed scheme was tested utilizing two well-known network datasets, NSL-KDD and UNSW-NB15. The suggested method beats other relevant methods in terms of accuracy, detection rate, and FPR by 99.0%, 99.0%, and 1.0%, respectively, for the NSL-KDD dataset, and 98.9%, 99.9%, and 1.1%, respectively, for the UNSW-NB15 dataset, according to the results of the performance comparison. Finally, simulation experiments using various evaluation metrics revealed that the suggested method is appropriate for IIOT intrusion network attack classification.

show abstract

Section: Deep Autoencoder (Dae)mentioning

confidence: 99%

“…An AE's simplest framework comprises three layers: input, secret, and output. If the training data ðx ðĩÞ Þ has n samples, each ðx ðĩÞ Þðiϵð1, ⋯, nÞÞ has several proportions, as well as a spatial function vector (d0); the Tanhinitiation function [85] is used and calculated using…”

Section: Deep Autoencoder (Dae)mentioning

confidence: 99%

Intrusion Detection in Industrial Internet of Things Network‐Based on Deep Learning Model with Rule‐Based Feature Selection

Awotunde

Chakraborty

Adeniyi

2021

Wireless Communications and Mobile Computing

127

View full text Add to dashboard Cite

show abstract

“…Ettercap [20,26], which is depicted in Figure 2, is mainly used in Kali Linux Devices. It is used to perform different types of attacks on our device that is running the Ettercap, used as a malicious node to perform the man-in-the-middle attack.…”

Section: Methodsmentioning

confidence: 99%

Automated diagnosis of attacks in internet of things using machine learning and frequency distribution techniques

2021

View full text Add to dashboard Cite

The Internet of Things (IoT) is the interconnection of things around us to make our daily process more efficient by providing more comfort and productivity. However, these connections also reveal a lot of sensitive data. Therefore, thinking about the methods of information security and coding are important as the security approaches that rely heavily on coding are not a strong match for these restricted devices. Consequently, this research aims to contribute to filling this gap, which adopts machine learning techniques to enhance network-level security in the low-power devices that use the lightweight MQTT protocol for their work. This study used a set of tools tools and, through various techniques, trained the proposed system ranging from Ensemble methods to deep learning models. The system has come to know what type of attack has occurred, which helps protect IoT devices. The log loss of the Ensemble methods is 0.44, and the accuracy of multi-class classification is 98.72% after converting the table data into an image set. The work also uses a Convolution Neural Network, which has a log loss of 0.019 and an accuracy of 99.3%. It also aims to implement these functions in IDS.

show abstract

“…Their system was evaluated on the KDD Cup 99 dataset, and the results showed that combining an autoencoder and DBN can achieve better detection accuracy than working with DBN alone. Tao et al [ 33 ] proposed a data fusion approach based on the Fisher score and deep autoencoder to reduce the dimensionality of data. Using the KDD Cup 99 dataset, it was confirmed that integrating the deep autoencoder as a feature extraction method can improve the accuracy of classification algorithms such as J48, the backpropagation neural network, and SVM.…”

Section: Related Workmentioning

confidence: 99%

Analysis of Autoencoders for Network Intrusion Detection

Song

Hyun

Cheong

2021

Sensors

View full text Add to dashboard Cite

As network attacks are constantly and dramatically evolving, demonstrating new patterns, intelligent Network Intrusion Detection Systems (NIDS), using deep-learning techniques, have been actively studied to tackle these problems. Recently, various autoencoders have been used for NIDS in order to accurately and promptly detect unknown types of attacks (i.e., zero-day attacks) and also alleviate the burden of the laborious labeling task. Although the autoencoders are effective in detecting unknown types of attacks, it takes tremendous time and effort to find the optimal model architecture and hyperparameter settings of the autoencoders that result in the best detection performance. This can be an obstacle that hinders practical applications of autoencoder-based NIDS. To address this challenge, we rigorously study autoencoders using the benchmark datasets, NSL-KDD, IoTID20, and N-BaIoT. We evaluate multiple combinations of different model structures and latent sizes, using a simple autoencoder model. The results indicate that the latent size of an autoencoder model can have a significant impact on the IDS performance.

show abstract

A Big Network Traffic Data Fusion Approach Based on Fisher and Deep Auto-Encoder

Cited by 28 publications

References 25 publications

Intrusion Detection in Industrial Internet of Things Network‐Based on Deep Learning Model with Rule‐Based Feature Selection

Intrusion Detection in Industrial Internet of Things Network‐Based on Deep Learning Model with Rule‐Based Feature Selection

Automated diagnosis of attacks in internet of things using machine learning and frequency distribution techniques

Analysis of Autoencoders for Network Intrusion Detection

Contact Info

Product

Resources

About