Research Article

Detection of Attacks in Network Traffic with the Autoencoder-Based Unsupervised Learning Method

Volume: 6 Number: 2 December 31, 2022
TR EN

Detection of Attacks in Network Traffic with the Autoencoder-Based Unsupervised Learning Method

Abstract

The effects of attacks on network systems and the extent of damages caused by them tend to increase every day. Solutions based on machine learning algorithms have started to be developed in order to develop appropriate defense systems by detecting attacks in a timely and effective manner. This study focuses on detecting abnormal traffic on networks through deep learning algorithms, and a deep autoencoder model architecture that can be used to detect attacks is recommended. To this end, an autoencoder model is first obtained by training the normal dataset without class labels in an unsupervised manner with an autoencoder, and a threshold value is obtained by running this model with small size test data with normal attack observations. The threshold value is calculated as a value that will optimize the model performance. It is observed that supervised learning methods lead to difficulties and cost increases in the detection of cyber-attacks and the labeling process. The threshold value is calculated using only small test data without resorting to labeling in order to overcome these costs and save time, and the incoming up-to-date network traffic information is classified based on this threshold value. 

Keywords

References

  1. Abadi, M., Agarval, A., Barham, P., Brevdo., Chen, A., Citro, C. ... Corrado, G.S. (2015), TensorFlow: Large-scale machine learning on heterogeneous systems, Software available from tensorflow.org, DOI: 10.5281/zenodo.4724125 google scholar
  2. Aygun, R. C., & Yavuz, A. G. (2017, June). Network anomaly detection with stochastically improved autoencoder based models. In 2017 IEEE 4th International Conference on Cyber Security and Cloud Computing (CSCloud) (pp. 193-198). IEEE. google scholar
  3. Chollet, F., & others. (2015). Keras. GitHub. Retrieved from https://github.com/fchollet/keras google scholar
  4. Chollet, F., (2019). Python ile Derin Öğrenme [Deep Learning with Python]. (Aksoy, B.A. Trans.). İstanbul, Turkey: Buzdağı yayınevi. google scholar
  5. CICIDS2017. (2017), Intrusion Detection Systems Datasets, Retrieved from https://www.unb.ca/cic/datasets/ids-2017.html google scholar
  6. Dutta,V., Pawlicki,M., Kozik,R. & Choras, M. (2022). Unsupervised network traffic anomaly detection with deep autoencoders, Logic Journal of the IGPL, jzac002. google scholar
  7. Gao M, Ma L , Liu H, Zhang Z, Ning Z & Xu, J. (2020). Malicious Network Traffic Detection Based on Deep Neural Networks and Association Analysis. Sensors.; 20(5):1452. https://doi.org/10.3390/s20051452 google scholar
  8. He, M., Wang, X., Zhou, J., Xi, Y., Jin, L., & Wang, X. (2021). Deep-Feature-Based Autoencoder Network for Few-Shot Malicious Traffic Detection. Security and Communication Networks, 2021. https://doi.org/10.1155/2021/6659022 google scholar

Details

Primary Language

English

Subjects

Computer Software

Journal Section

Research Article

Publication Date

December 31, 2022

Submission Date

July 9, 2022

Acceptance Date

October 14, 2022

Published in Issue

Year 2022 Volume: 6 Number: 2

APA
Özkan, Y. (2022). Detection of Attacks in Network Traffic with the Autoencoder-Based Unsupervised Learning Method. Acta Infologica, 6(2), 199-207. https://doi.org/10.26650/acin.1142806
AMA
1.Özkan Y. Detection of Attacks in Network Traffic with the Autoencoder-Based Unsupervised Learning Method. ACIN. 2022;6(2):199-207. doi:10.26650/acin.1142806
Chicago
Özkan, Yalçın. 2022. “Detection of Attacks in Network Traffic With the Autoencoder-Based Unsupervised Learning Method”. Acta Infologica 6 (2): 199-207. https://doi.org/10.26650/acin.1142806.
EndNote
Özkan Y (December 1, 2022) Detection of Attacks in Network Traffic with the Autoencoder-Based Unsupervised Learning Method. Acta Infologica 6 2 199–207.
IEEE
[1]Y. Özkan, “Detection of Attacks in Network Traffic with the Autoencoder-Based Unsupervised Learning Method”, ACIN, vol. 6, no. 2, pp. 199–207, Dec. 2022, doi: 10.26650/acin.1142806.
ISNAD
Özkan, Yalçın. “Detection of Attacks in Network Traffic With the Autoencoder-Based Unsupervised Learning Method”. Acta Infologica 6/2 (December 1, 2022): 199-207. https://doi.org/10.26650/acin.1142806.
JAMA
1.Özkan Y. Detection of Attacks in Network Traffic with the Autoencoder-Based Unsupervised Learning Method. ACIN. 2022;6:199–207.
MLA
Özkan, Yalçın. “Detection of Attacks in Network Traffic With the Autoencoder-Based Unsupervised Learning Method”. Acta Infologica, vol. 6, no. 2, Dec. 2022, pp. 199-07, doi:10.26650/acin.1142806.
Vancouver
1.Yalçın Özkan. Detection of Attacks in Network Traffic with the Autoencoder-Based Unsupervised Learning Method. ACIN. 2022 Dec. 1;6(2):199-207. doi:10.26650/acin.1142806