Intelligent Intrusion Detection Method of Industrial Internet of Things Based on CNN-BiLSTM

Li, Aichuan; Yi, Shujuan

doi:10.1155/2022/5448647

Cited by 12 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the BiLSTM recurrent bidirectional architecture, the BiLSTM and CNN layers in this architecture are accountable for learning the temporal and spatial relationship respectively between the network flow and adjusting the temporal and spatial dynamics [18]. These layers also provide the framework for network flow feature extraction.…”

Section: Proposed Hybrid Bilstm-cnn Modelmentioning

confidence: 99%

BiLSTM-CNN Hybrid Intrusion Detection System for IoT Application

Sadhwani,

Khan,

Muthalagu

et al. 2024

Preprint

View full text Add to dashboard Cite

Intrusions in computer networks have increased significantly in recent times and network security mechanisms are not being developed at the same pace at which intrusion attacks are evolving. Therefore, a need has arisen to improve intrusion detection systems (IDS) to make network secure. This research focuses on anomaly-based IDS for security assaults. In this research, deep learning techniques such as Bi-directional Long Short-Term Memory (Bi-LSTM) and Convolutional Neural Networks (CNN) are implemented and subsequently used to design a novel BiLSTM-CNN hybrid IDS for the Internet of Things (IoT). The hybrid intrusion detection system model is created by utilizing the advantages of both the BiLSTM and the CNN's ability to extract temporal and spatial features respectively. The research uses the UNSW-NB 15 dataset for proposed deep learning IDS for IoT networks. The dataset has been split into training and testing data for classifying traffic into normal or attack classes. The models are run on GPU and CPU to illustrate their efficacy and match real-world IoT network communication behavior. The BiLSTM, CNN, and hybrid BiLSTM-CNN models are assessed on various aspects like Precision, Sensitivity, F1-Score, Miscalculation Rate, False Positive Rate, False Negative Rate, and Matthews Correlation Coefficient to evaluate the model’s robustness. The findings revealed that the hybrid model surpassed the BiLSTM and CNN models in all aspects. Additionally, the proposed model is compared with the cutting-edge existing approaches in terms of different performance metrics and proved to be better than state-of-the-art models.

show abstract

Section: Proposed Hybrid Bilstm-cnn Modelmentioning

confidence: 99%

BiLSTM-CNN Hybrid Intrusion Detection System for IoT Application

Sadhwani,

Khan,

Muthalagu

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…An improved intelligent intrusion detection method was investigated in [31] via DL. However, the efficient algorithms failed to improve the accuracy of the designed model.…”

Section: Related Workmentioning

confidence: 99%

Enhancing data security in cloud computing: a blockchain-based Feistel cipher encryption and multiclass vector side-channel attack detection approach

2024

IJATEE

View full text Add to dashboard Cite

Cloud computing (CC) permits more users for storing as well as distributing their applications and data. CC continuously evolving technology that can improve agility, availability, collaboration, and scalability of data. It offers on-demand solution for different applications namely data storage, servers, databases, networking, and software. One of the most challenging issues in CC is detecting attacks. Parallel sponge-based authenticated encryptionwith sidechannel protection and adversary-invisible nonces (PSASPIN) to sponge construction was designed [1]. Moreover, leveled implementation has also utilized in implementing key generation via pseudo random function (PRF). Next, data preprocessing has utilized to minimize the code size. Finally, security proof has ensured using game theory and therefore processing shorter messages significantly. The authenticated encryption (AE) schemes such as security, performance, and efficiency are enhanced.*Author for correspondence Despite improvement found in terms of communication complexity and throughput were not focused.Side channel assault also utilizes physical data which leaks as of cryptographic tool. For avoiding from these attacks, divide-and-conquer approach is employed. Here, malicious user splits key into subkeys, endeavors for recuperating sub-keys distinctly as well as integrates them to create key. Reinforcement-strategy-based side-channel attack has designed in [2] with divide-and-conquer. Initially, the power leakage models are modified, and accuracy has improved. Next, the recovered sub-keys are integrated during the attack phase through validation therefore mitigating side-channel attacks significantly and improving the successful recovery rate. Though successful recovery rate has ensured but the detection time and accuracy have not focused. The disclosure of the cloud storage in the recent years carries enormous east to person life. Moreover, business establishments as well as organizations transmitted huge data for storage also. However, the data privacy

show abstract

“…Recently, several DL-based methods have been proposed to improve the feature extraction ability of abnormal traffic in IoT environment. For industrial IoT security, reference (Li et al, 2022) proposed an intelligent NID system based on improved bidirectional short-term memory network (Bi-LSTM), and the network training speed is accelerated through the Batch Normalization mechanism. However, this method does not take into account the weight calculation of different data attribute features.…”

Section: Related Workmentioning

confidence: 99%

A Network Intrusion Detection Method Based on Improved Bi-LSTM in Internet of Things Environment

Fan

2023

International Journal of Information Technologies and Systems Approach

View full text Add to dashboard Cite

When performing malicious network attack detection, traditional intrusion detection methods show their disadvantage of low accuracy and high false detection rate. To address these problems, this paper proposes a novel network intrusion detection scheme based on an improved bi-directional long short-term memory (Bi-LSTM) model under the emerging internet of things (IoT) environment. Firstly, this paper analyzes Bi-LSTM model. Then, it introduces a two-layer attention network structure into Bi-LSTM network. Finally, the corresponding network intrusion detection system is constructed based on the improved Bi STM model. Through simulation experiments, the proposed network intrusion detection method and other three methods are compared under five identical databases. Experimental results show that the false detection rate and detection accuracy of the proposed method are optimal on all sample data, the detection accuracy reaches 97.24% and the false detection rate drops to 5.13%.

show abstract

Intelligent Intrusion Detection Method of Industrial Internet of Things Based on CNN-BiLSTM

Cited by 12 publications

References 29 publications

BiLSTM-CNN Hybrid Intrusion Detection System for IoT Application

BiLSTM-CNN Hybrid Intrusion Detection System for IoT Application

Enhancing data security in cloud computing: a blockchain-based Feistel cipher encryption and multiclass vector side-channel attack detection approach

A Network Intrusion Detection Method Based on Improved Bi-LSTM in Internet of Things Environment

Contact Info

Product

Resources

About