PDAE: Efficient network intrusion detection in IoT using parallel deep auto-encoders

Basati, Amir; Faghih, Mohammad Mehdi

doi:10.1016/j.ins.2022.03.065

Cited by 39 publications

(20 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Te accuracy and detection rate of the method were improved compared to traditional algorithms. Basati and Faghih [5] proposed a novel lightweight architecture-parallel deep autoencoder (PDAE) that aims to construct nearest neighbor values and nearest neighbor information for each feature vector. Te efectiveness of the proposed architecture was evaluated using the KDDCup99, UNSW-NB15, and CICIDS2017 datasets, and the evaluation results showed that the proposed model was efective in improving accuracy and performance.…”

Section: Introductionmentioning

confidence: 99%

Research on Boruta-ET-Based Anomalous Traffic Detection Model

Huang

Zhang

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

With the rapid development of networks, intrusion detection has received increasing attention. In order to solve the problems of large dimensionality of intrusion detection data, unbalanced data samples, and large dispersion of datasets, which seriously affect the classification performance, this study proposes an anomaly detection based on Boruta and extreme tree (Boruta-ET) model. First, the network traffic data are preprocessed, which includes data cleaning, numerical and normalization processes, as well as equalization of the attack categories for a small number of samples by random oversampling at the data level; second, the traffic features are dimensionality reduced using the Boruta-based algorithm. The goal of Boruta dimensionality reduction is to extract all the features related to the dependent variable with a global dimension and find the optimal subset of features containing the most information; finally, the optimal feature subset is used as the input parameters of the extreme tree (ET) algorithm model for training and testing. Experiments were conducted on the real network traffic dataset CICIDS2017, and by evaluating the classification performance of several different machine learning algorithms, the experimental results show that the Boruta-ET model has the best performance with an accuracy rate of 99.80%, which can effectively improve the detection rate and achieve an effective recall rate for attack types with a small number of samples.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on Boruta-ET-Based Anomalous Traffic Detection Model

Huang

Zhang

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…The proposed model utilizes a stacking ensemble of four DL models integrated into a deep fully connected layer. Additionally, a novel and efficient structure utilizing Parallel Deep Auto-Encoder (PDAE) is introduced in [34]. The suggested model incorporates local and surrounding information to enhance model accuracy and minimize the parameters' number, memory usage, and processing requirements.…”

Section: Related Workmentioning

confidence: 99%

DCNN: A Novel Binary and Multi-Class Network Intrusion Detection Model via Deep Convolutional Neural Network

Shebl,

Elsedimy,

Ismail

et al. 2024

Preprint

View full text Add to dashboard Cite

Network security has become imperative in the context of our interconnected networks and everyday communications. Recently, many deep learning models have been proposed to tackle the problem of predicting intrusions and malicious activities in interconnected systems. However, they solely focus on binary classification and lack reporting on individual class performance in case of multi-class classification. Therefore, the need for an efficient and accurate network intrusion detection system has reached a pivotal point. In this paper, we propose a novel intelligent detection system based on convolutional neural network, namely DCNN. The proposed model can be utilized to analyze and detect attacks and intrusions in intelligent network systems. The DCNN model is applied against two benchmark datasets and compared with state-of-the-art models. Experimental results show that the proposed model improved resilience to intrusions and malicious activities for binary as well as multi-class classification. Furthermore, our DCNN model outperforms similar intrusion detection systems in terms of positive predicted value, true positive rate, F1 measure, and accuracy. The scores obtained for binary and multi-class classifications on the CICIoT2023 dataset are 99.50% and 99.25%, respectively. Additionally, for the CICIDS-2017 dataset, DCNN attains a score of 99.96% for both binary and multi-class classifications.

show abstract

“…Their system comprises three critical engines, facilitating effective attack detection and classification. Basati et al [ 22 ] proposed a Network-based Intrusion Detection System (NIDS) built upon deep neural networks specifically designed for IoT networks. The Parallel Deep Auto-Encoder (PDAE) model enhances accuracy while significantly reducing computational requirements.…”

Section: Related Workmentioning

confidence: 99%

Security at the Edge for Resource-Limited IoT Devices

Canavese,

Mannella,

Regano

et al. 2024

Sensors

View full text Add to dashboard Cite

The Internet of Things (IoT) is rapidly growing, with an estimated 14.4 billion active endpoints in 2022 and a forecast of approximately 30 billion connected devices by 2027. This proliferation of IoT devices has come with significant security challenges, including intrinsic security vulnerabilities, limited computing power, and the absence of timely security updates. Attacks leveraging such shortcomings could lead to severe consequences, including data breaches and potential disruptions to critical infrastructures. In response to these challenges, this research paper presents the IoT Proxy, a modular component designed to create a more resilient and secure IoT environment, especially in resource-limited scenarios. The core idea behind the IoT Proxy is to externalize security-related aspects of IoT devices by channeling their traffic through a secure network gateway equipped with different Virtual Network Security Functions (VNSFs). Our solution includes a Virtual Private Network (VPN) terminator and an Intrusion Prevention System (IPS) that uses a machine learning-based technique called oblivious authentication to identify connected devices. The IoT Proxy’s modular, scalable, and externalized security approach creates a more resilient and secure IoT environment, especially for resource-limited IoT devices. The promising experimental results from laboratory testing demonstrate the suitability of IoT Proxy to secure real-world IoT ecosystems.

show abstract

PDAE: Efficient network intrusion detection in IoT using parallel deep auto-encoders

Cited by 39 publications

References 25 publications

Research on Boruta-ET-Based Anomalous Traffic Detection Model

Research on Boruta-ET-Based Anomalous Traffic Detection Model

DCNN: A Novel Binary and Multi-Class Network Intrusion Detection Model via Deep Convolutional Neural Network

Security at the Edge for Resource-Limited IoT Devices

Contact Info

Product

Resources

About