A hybrid Deep Learning Strategy for an Anomaly Based N-IDS

Mennour, Hanene; Mostefai, Sihem

doi:10.1109/iscv49265.2020.9204227

Cited by 6 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…C72 [105] CICIDS2017 datasets e model outperformed other intrusion detection models in terms of detection rate, accuracy, and false-positive-rate.…”

Section: C70mentioning

confidence: 97%

A Systematic Review on Hybrid Intrusion Detection System

Maseno

Wang

Xing

2022

Security and Communication Networks

View full text Add to dashboard Cite

As computer networks keep growing at a high rate, achieving confidentiality, integrity, and availability of the information system is essential. Intrusion detection systems (IDSs) have been widely used to monitor and secure networks. The two major limitations facing existing intrusion detection systems are high rates of false-positive alerts and low detection rates on zero-day attacks. To overcome these problems, we need intrusion detection techniques that can learn and effectively detect intrusions. Hybrid methods based on machine learning techniques have been proposed by different researchers. These methods take advantage of the single detection methods and leverage their weakness. Therefore, this paper reviews 111 related studies in the period between 2012 and 2022 focusing on hybrid detection systems. The review points out the existing gaps in the development of hybrid intrusion detection systems and the need for further research in this area.

show abstract

“…C72 [105] CICIDS2017 datasets e model outperformed other intrusion detection models in terms of detection rate, accuracy, and false-positive-rate.…”

Section: C70mentioning

confidence: 97%

A Systematic Review on Hybrid Intrusion Detection System

Maseno

Wang

Xing

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…[28] and [29] combine two deep learning models, DNN and stacked auto-encoder (SAE), to apply them to the IDS. However, [28] introduces an additional attention mechanism to construct an SAAE-DNN model.…”

Section: A Deep Neural Networkmentioning

confidence: 99%

“…However, [28] introduces an additional attention mechanism to construct an SAAE-DNN model. Moreover, the ReLu function serves as the activation function of the hidden layer in [28], whereas the activation function of the hidden layer in [29] is the tanh function. Both [28] and [29] employ DNN as classification algorithms to carry out the classification task for detecting intrusions.…”

Section: A Deep Neural Networkmentioning

confidence: 99%

“…Moreover, the ReLu function serves as the activation function of the hidden layer in [28], whereas the activation function of the hidden layer in [29] is the tanh function. Both [28] and [29] employ DNN as classification algorithms to carry out the classification task for detecting intrusions. Table I demonstrates that the accuracy of the IDS with DNN in detecting 2-classes of data in the NSL-KDD dataset exceeds the accuracy in detecting multi-classes of data, which is attributable to the data imbalance problem inherent in the NSL-KDD dataset.…”

Section: A Deep Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Deep Learning Technologies for Intrusion Detection in Internet of Things

Liao,

Murah,

Hasan

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Internet of Things (IoT) is transforming how we live and work and its applications are widespread, spanning smart homes, industrial monitoring, smart cities, healthcare, agriculture, and retail Considering its wide range applications, it is vital to address the security challenges arising from the massive collection and transmission of user data by IoT devices. Intrusion detection systems (IDS) based on deep learning techniques offer new means and research directions for resolving IoT security issues. Deep learning models can process large volumes of data and extract complex patterns, making them generally more effective than traditional rule based IDSs. While deep learning techniques are gradually gaining popularity in IDS applications, current research lacks a comprehensive summary of deep learning-based IDS in the context of IoT. This paper provides an introduction to intrusion detection technologies, followed by a detailed comparison, analysis, and discussion of deep learning models, datasets, feature extraction and classifiers, data preprocessing techniques, and experimental design of the models. It also highlights the current challenges and issues associated with deep learning models and relevant techniques for IDS. Finally, it concludes by providing recommendations to assist researchers in this domain.

show abstract

“…The use of autoencoder in the pre-training stage to achieve dimensional reduction was considered by Mennour and Mostefai (2020) in their network-based intrusion detection system and the output was then used to train Deep Neural Network (DNN). Mennour and Mostefai (2020) made use of CICIDS2017 datasets in their work and the result was better than two state-of-art IDS.…”

Section: Fig 1: Position Of Ids In An Organization's Edge Networkmentioning

confidence: 99%