Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study

By Mohamed Amine Ferrag, Leandros A. Maglaras, Sotiris K. Moschoyiannis, Helge Janicke. Journal of Information Security and Applications, 2020

1,092 citations recorded by the source corpus.

Abstract In this paper, we present a survey of deep learning approaches for cyber security intrusion detection, the datasets used, and a comparative study. Specifically, we provide a review of intrusion detection systems based on deep learning approaches. The dataset plays an important role in intrusion detection, therefore we describe 35 well-known cyber datasets and provide a classification of these datasets into seven categories; namely, network traffic-based dataset, electrical network-based dataset, internet traffic-based dataset, virtual private network-based dataset, android apps-based dataset, IoT traffic-based dataset, and internet-connected devices-based dataset. We analyze seven deep learning models including recurrent neural networks, deep neural networks, restricted Boltzmann machines, deep belief networks, convolutional neural networks, deep Boltzmann machines, and deep autoencoders. For each model, we study the performance in two categories of classification (binary and multiclass) under two new real traffic datasets, namely, the CSE-CIC-IDS2018 dataset and the Bot-IoT dataset. In addition, we use the most important performance indicators, namely, accuracy, false alarm rate, and detection rate for evaluating the efficiency of several methods.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

View Paper: https://www.semanticscholar.org/paper/1a54a6486d8e4c906e6a334157ee6832ad01871c

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

1. Md. Hasan Furhad
2. V. Varadharajan
3. Helge Janicke
4. Suhuai Luo
5. Raza Nowrozy
6. Min Xu
7. Ibrahim A. Hameed
8. Mohamed Amine Ferrag

In Computer Networks and Communications

1. Iqbal H. Sarker
2. V. Varadharajan
3. Helge Janicke
4. Suhuai Luo
5. Min Xu
6. Ibrahim A. Hameed
7. Mohamed Amine Ferrag
8. Kamran Shaukat

In Signal Processing

1. Iqbal H. Sarker
2. V. Varadharajan
3. Helge Janicke
4. Mohamed Amine Ferrag

Citations in the corpus

• Edge-IIoTset: A New Comprehensive Realistic Cyber Security Dataset of IoT and IIoT Applications for Centralized and Federated Learning (2022, background): “*There are other cyber security datasets used by security researchers for evaluating artificial intelligence-based security systems in different IoT and IIoT applications, such as ISCX, DARPA-2009, CICDS2017, UNSW-NB15, KDD99, and NSL-KDD [13].”
• A Survey on Machine Learning Techniques for Cyber Security in the Last Decade (2020, methodology): “CICIDS2017 is another dataset collected from 03-07 July 2017 contains various attack scenarios implemented by this dataset, including DoS, Web attack, and Botnet [48].”
• AI-Driven Cybersecurity: An Overview, Security Intelligence Modeling and Research Directions (2021, background): “The researchers of [91] review deep learning for the detection of cyber security intrusion.”