Title: Network Attack Detection Method Based on Their Time - Frequency Decomposition

Issue Number: Vol. 8, No. 4
Year of Publication: Dec - 2019
Page Numbers: 273-278
Authors: Dimitris Sklavounos, Spiros Chountasis, Aloysius Edoh
Journal Name: International Journal of Cyber-Security and Digital Forensics (IJCSDF)
- Hong Kong
DOI:  http://dx.doi.org/10.17781/P002630


In the last few years, attack detection has become a powerful methodology for network protection and network security measures. The present work presents a new detection scheme for data recorded over the network, applicable on the broad scientific field of information security, including detection and prevention. The proposed method employs bi-dimensional (time-frequency) data representations of the forms of the Short Time Fourier transform (STFT) as well as the Wigner Distribution (WD). Moreover, the method applies factorization and Singular Value Decomposition (SVD) of these two-dimensional matrices in order to achieve intrusion detection. The current scheme was performed and evaluated for the case of a dataset KDD-NSL and the efficiency and robustness of the procedure is proven experimentally.