A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks

By Chuanlong Yin, Yuefei Zhu, Jin-long Fei, Xin-Zheng He. IEEE Access, 2017

1,676 citations recorded by the source corpus.

Intrusion detection plays an important role in ensuring information security, and the key technology is to accurately identify various attacks in the network. In this paper, we explore how to model an intrusion detection system based on deep learning, and we propose a deep learning approach for intrusion detection using recurrent neural networks (RNN-IDS). Moreover, we study the performance of the model in binary classification and multiclass classification, and the number of neurons and different learning rate impacts on the performance of the proposed model. We compare it with those of J48, artificial neural network, random forest, support vector machine, and other machine learning methods proposed by previous researchers on the benchmark data set. The experimental results show that RNN-IDS is very suitable for modeling a classification model with high accuracy and that its performance is superior to that of traditional machine learning classification methods in both binary and multiclass classification. The RNN-IDS model improves the accuracy of the intrusion detection and provides a new research method for intrusion detection.

Subfields: Artificial Intelligence, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/0ef9ae1ce8c91ce671a211bdda792bf3752d1522

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

Citations in the corpus

Machine Learning and Deep Learning Methods for Cybersecurity (2018, methodology): “[63] propose intrusion detection (RNN-IDS) based on a cyclic neural network.”
Network Intrusion Detection Combined Hybrid Sampling With Deep Hierarchical Network (2020, methodology): “RNN is a commonly used model in deep learning [21].”
Deep Learning Approach Combining Sparse Autoencoder With SVM for Network Intrusion Detection (2018, methodology): “The authors compared the results of their model with those of many classification algorithms discussed in [22] and [35], as demonstrated in Table 9 and Table 10.”
Benchmarking of Machine Learning for Anomaly Based Intrusion Detection Systems in the CICIDS2017 Dataset (2021, background): “Therefore, a comparative analysis of these models by using a recently developed dataset is necessary to evaluate their efﬁciency in distinguishing malicious from benign activities and in identifying different types of attacks [13].”
BAT: Deep Learning Methods on Network Intrusion Detection Using NSL-KDD Dataset (2020, methodology): “1% higher than CNN [54] and RNN [52], respectively.”
Deep Learning Approach for Intelligent Intrusion Detection System (2019, methodology): “Overall, a comprehensive literature review shows very few studies use modern deep learning approaches for NIDS and the commonly used benchmark datasets for experimental analysis are KDDCup 99 and NSL-KDD [3], [32]–[34].”
Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study (2020, background): “Yin et al. [34] attemtped to integrate a recurrent neural network in an IDS system for supervised classiﬁcation learning.”
Lucid: A Practical, Lightweight Deep Learning Solution for DDoS Attack Detection (2020, methodology): “In [48], a Recurrent Neural Network (RNN)-Intrusion Detection System (IDS) is compared with a series of previously presented ML techniques (e.g. J48, Artiﬁcial Neural Network (ANN), Random Forest, and SVM) applied to the NSL-KDD [49] dataset.”
Network intrusion detection system: A systematic study of machine learning and deep learning approaches (2020, methodology): “RNN-based IDS was proposed by Yin et al 91 in the context of binary and multi class classification of the NSL-KDD dataset.”
CNN-Based Network Intrusion Detection against Denial-of-Service Attacks (2020, methodology): “[28] perform the binary classification and multiclass classification based on RNN which is one of DL models.”
Adversarial Machine Learning for Network Intrusion Detection Systems: A Comprehensive Survey (2023, methodology): “However, despite the RNN-based advances in the NLP domain, NIDS designs with RNN as the detection algorithm still use LSTM models or plain RNN for detection [41], [53], [55].”