A Deep Learning Framework for Predicting Cyber Attacks Rates

Authors

Xing Fang, Illinois State UniversityFollow
Maochao Xu
Shouhuai Xu
Peng Zhao

Document Type

Article

Publication Title

EURASIP Journal on Information Security

Publication Date

2019

Keywords

ARIMA, GARCH, RNN, Hybrid models, LSTM, Deep learning, BRNN-LSTM

Abstract

Like how useful weather forecasting is, the capability of forecasting or predicting cyber threats can never be overestimated. Previous investigations show that cyber attack data exhibits interesting phenomena, such as long-range dependence and high nonlinearity, which impose a particular challenge on modeling and predicting cyber attack rates. Deviating from the statistical approach that is utilized in the literature, in this paper we develop a deep learning framework by utilizing the bi-directional recurrent neural networks with long short-term memory, dubbed BRNN-LSTM. Empirical study shows that BRNN-LSTM achieves a significantly higher prediction accuracy when compared with the statistical approach.

Comments

First published in EURASIP Journal on Information Security (2019) 2019:5. https://doi.org/10.1186/s13635-019-0090-6.

Data used in this work is not suitable for public use. The source code used in the present paper is available at https://github.com/xingfang912/time-series- analysis.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

DOI

10.1186/s13635-019-0090-6

Recommended Citation

Fang, Xing; Xu, Maochao; Xu, Shouhuai; and Zhao, Peng, "A Deep Learning Framework for Predicting Cyber Attacks Rates" (2019). Faculty Publications - Information Technology. 2.
https://ir.library.illinoisstate.edu/fpitech/2