A Residual Learning-Based Network Intrusion Detection System

Man, Jiarui; Sun, Guozi

doi:10.1155/2021/5593435

Cited by 35 publications

(14 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, they also proposed a filtration technique that has the capability of enhancing the performance in terms of reduction of false alarm rate. Man and Sun [17] proposed a residual learning-based intrusion detection model. ey utilized a modified focal loss function to deal with the class imbalance problem existing in the UNSW-NB15 dataset.…”

Section: Literature Surveymentioning

confidence: 99%

Detecting Temporal Attacks: An Intrusion Detection System for Train Communication Ethernet Based on Dynamic Temporal Convolutional Network

Yue

Wang

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

The train communication Ethernet (TCE) of modern intelligent trains is under an ever-increasing threat of serious network attacks. Denial of service (DoS) and man in the middle (MITM), the two most destructive attacks against TCE, are difficult to detect by conventional methods. Aiming at their highly time-correlated properties, a novel dynamic temporal convolutional network-based intrusion detection system (DyTCN-IDS) is proposed in this paper to detect these temporal attacks. A semiphysical TCE testbed that is capable of simulating real situations in TCE-based trains is first built to generate an effective dataset for training and testing. DyTCN-IDS consists of two phases, and in the first phase, systematic feature engineering is designed to optimize the dataset. In the second phase, a basic detection model that is good at dealing with temporal features is first built by utilizing the temporal convolutional network with several architectural optimizations. Then, in order to decrease the computational consumption waste on network packet sequences with different lengths of inner temporal relationships, dynamic neural network technology is further adopted to optimize the basic detection model. Diverse experiments were carried out to evaluate the proposed system from different angles. The experimental results indicate that our system is easy to train, converges fast, costs less computational resources, and achieves satisfying detection performance with a macro false alarm rate of 0.09%, a macro F-score of 99.39%, and an accuracy of 99.40%. Compared to some canonical DL-based IDS and some latest IDS, our system acquires the best overall detection performance as well.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Detecting Temporal Attacks: An Intrusion Detection System for Train Communication Ethernet Based on Dynamic Temporal Convolutional Network

Yue

Wang

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…However, the network depth increase can be the source of the gradient explosion phenomenon, and the network performance degradation. According to literature results [45], the simple fact of adding pooling and convolution layers to the network does not help in improving the network accuracy but rather conducts to a degradation of the network performance. In this paper, to solve the above problem, we use residual learning.…”

Section: Residual Dnn Blockmentioning

confidence: 99%

Residual Autoencoder Deep Neural Network for Electrical Capacitance燭omography

Deabes¹,

Bouazza²

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Great achievements have been made during the last decades in the field of Electrical Capacitance Tomography (ECT) image reconstruction. However, there is still a need to make these image reconstruction results faster and of better quality. Recently, Deep Learning (DL) is flourishing and is adopted in many fields. The DL is very good at dealing with complex nonlinear functions and it is built using several series of Artificial Neural Networks (ANNs). An ECT image reconstruction model using DNN is proposed in this paper. The proposed model mainly uses Residual Autoencoder called (ECT_ResAE). A large-scale dataset of 320 k instances have been generated to train and test the proposed ECT_ResAE model. Each instance contains two vectors; a distinct permittivity distribution and its corresponding capacitance measurements. The capacitance vector has been modulated to generate a 66×66 image, and represented to the ECT_ResAE as an input. The scalability and practicability of the ECT_ResAE network are tested using noisy data, new samples, and experimental data. The experimental results show that the proposed ECT_ResAE image reconstruction model provides accurate reconstructed images. It achieved an average image Correlation Coefficient (CC) of more than 99% and an average Relative Image Error (IE) around 8.5%.

show abstract

“…To address the imbalanced data problem, either over-or undersampling strategy has been proposed to balance the training data [12][13][14]. However, each strategy has its own weakness in practice.…”

Section: Introductionmentioning

confidence: 99%

A Few‐Shot Learning‐Based Siamese Capsule Network for Intrusion Detection with Imbalanced Training Data

Wang

Tian

Qin

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Network intrusion detection remains one of the major challenges in cybersecurity. In recent years, many machine-learning-based methods have been designed to capture the dynamic and complex intrusion patterns to improve the performance of intrusion detection systems. However, two issues, including imbalanced training data and new unknown attacks, still hinder the development of a reliable network intrusion detection system. In this paper, we propose a novel few-shot learning-based Siamese capsule network to tackle the scarcity of abnormal network traffic training data and enhance the detection of unknown attacks. In specific, the well-designed deep learning network excels at capturing dynamic relationships across traffic features. In addition, an unsupervised subtype sampling scheme is seamlessly integrated with the Siamese network to improve the detection of network intrusion attacks under the circumstance of imbalanced training data. Experimental results have demonstrated that the metric learning framework is more suitable to extract subtle and distinctive features to identify both known and unknown attacks after the sampling scheme compared to other supervised learning methods. Compared to the state-of-the-art methods, our proposed method achieves superior performance to effectively detect both types of attacks.

show abstract

A Residual Learning-Based Network Intrusion Detection System

Cited by 35 publications

References 31 publications

Detecting Temporal Attacks: An Intrusion Detection System for Train Communication Ethernet Based on Dynamic Temporal Convolutional Network

Detecting Temporal Attacks: An Intrusion Detection System for Train Communication Ethernet Based on Dynamic Temporal Convolutional Network

Residual Autoencoder Deep Neural Network for Electrical Capacitance燭omography

A Few‐Shot Learning‐Based Siamese Capsule Network for Intrusion Detection with Imbalanced Training Data

Contact Info

Product

Resources

About