A multiscale intrusion detection system based on pyramid depthwise separable convolution neural network

He, Jiaxing; Wang, Xiaodan; Song, Yafei; Xiang, Qian

doi:10.1016/j.neucom.2023.01.072

Cited by 21 publications

(11 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, Tayfour et al [67] explored the use of a Deep Learning (DL) approach through a Long Short-Term Memory (DL-LSTM) architecture aimed at recognizing cyber-attacks targeting IoT and 5G networks, achieving significant accuracy improvements on the CICIDS2017 dataset and showcasing the DL model's capability in accurately identifying network intrusions. Additionally, He et al [68] developed an IDS based on a Pyramid Depthwise Separable Convolution neural network (PyDSC-IDS), which, when compared to other DL approaches, delivered superior accuracy in detecting network intrusions with minimal added complexity across various datasets including NSL-KDD, UNSW-NB15, and CICIDS2017, further highlighting the advancements and effectiveness of DL techniques in the realm of intrusion detection systems.…”

Section: Automl-enabled Autonomous Cybersecurity Mechanismsmentioning

confidence: 99%

See 1 more Smart Citation

Enabling AutoML for Zero-Touch Network Security: Use-Case Driven Analysis

Yang,

Rajab,

Shami

et al. 2024

Preprint

View full text Add to dashboard Cite

Zero-Touch Networks (ZTNs) represent a state-of-the-art paradigm shift towards fully automated and intelligent network management, enabling the automation and intelligence required to manage the complexity, scale, and dynamic nature of next-generation (6G) networks. ZTNs leverage Artificial Intelligence (AI) and Machine Learning (ML) to enhance operational efficiency, support intelligent decision-making, and ensure effective resource allocation. However, the implementation of ZTNs is subject to security challenges that need to be resolved to achieve their full potential. In particular, two critical challenges arise: the need for human expertise in developing AI/ML-based security mechanisms, and the threat of adversarial attacks targeting AI/ML models. In this survey paper, we provide a comprehensive review of current security issues in ZTNs, emphasizing the need for advanced AI/ML-based security mechanisms that require minimal human intervention and protect AI/ML models themselves. Furthermore, we explore the potential of Automated ML (AutoML) technologies in developing robust security solutions for ZTNs. Through case studies, we illustrate practical approaches to securing ZTNs against both conventional and AI/ML-specific threats, including the development of autonomous intrusion detection systems and strategies to combat Adversarial ML (AML) attacks. The paper concludes with a discussion of the future research directions for the development of ZTN security approaches. Abstract content goes here

show abstract

Section: Automl-enabled Autonomous Cybersecurity Mechanismsmentioning

confidence: 99%

“…For instance, as described in Section IV-D, the DL-LSTM model proposed in [67] and the PyDSC-IDS model proposed in [68] achieved high accuracy and F1scores of more than 99.3% on the CICIDS2017 dataset.…”

Section: B Use Case 1: Automl-based Automated Ids 1) Experimental Setupmentioning

confidence: 99%

Enabling AutoML for Zero-Touch Network Security: Use-Case Driven Analysis

Yang,

Rajab,

Shami

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…This paper proposes an improved lightweight TCN module to solve these problems. The lightweight TCN module uses depthwise separable convolution [13] instead of traditional convolution, constructs a causal dilated depth-separable convolution layer, and uses the Leaky ReLU [14]…”

Section: Multiscale Temporal Data Extraction Partmentioning

confidence: 99%

Lightweight Human Motion Recognition Method with Multiscale Temporal Features

Liu,

Luan

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

To address the problems of the large size of human motion recognition models based on deep learning and insufficient mining of data features and thus low recognition accuracy, a lightweight human motion recognition algorithm based on multi-scale temporal features is proposed, the algorithm automatically extracted features through a multiscale feature fusion model. After, the integrated features are modeled by an improved time convolution network (TCN). In the TCN network structure, In the TCN network structure, the depthwise separable convolution is used instead of the normal convolutional layer to reduce the computational complexity, and the Leaky ReLU activation function is used instead of the ReLU function to improve the training efficiency. The experiments are based on the WISDM public dataset. finally achieve fast real-time recognition of actions, and structural and parametric optimization is performed through experiments to effectively improve the accuracy of results, and the final accuracy rate reaches 99.06%. In comparison with other methods, this method can reduce the model volume while maintaining a high accuracy rate.

show abstract

“…Furthermore, monitoring the performance of each class is imperative in order to guarantee that the model is functioning effectively across all class. However, many models lack reporting on the performance of individual classes in multi-class classification (e.g., see [6,[28][29][30][31][32]). Hence, resulting in an incomplete comprehension of the model's performance.…”

Section: Introductionmentioning

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

A multiscale intrusion detection system based on pyramid depthwise separable convolution neural network

Cited by 21 publications

References 12 publications

Enabling AutoML for Zero-Touch Network Security: Use-Case Driven Analysis

Enabling AutoML for Zero-Touch Network Security: Use-Case Driven Analysis

Lightweight Human Motion Recognition Method with Multiscale Temporal Features

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

Contact Info

Product

Resources

About