Intrusion Prediction using Long Short-Term Memory Deep Learning with UNSW-NB15

Seongsoo Kim, Lei Chen, Jongyeop Kim

Research output: Contribution to book or proceedingConference articlepeer-review

1 Scopus citations

Abstract

This study shows the effectiveness of anomaly-based IDS using long short-Term memory(LSTM) based on the newly developed dataset called UNSW-NB15 while considering root mean square error and mean absolute error as evaluation metrics for accuracy. For each attack, 80% and 90% of samples were used as LSTM inputs and trained this model while increasing epoch values. Furthermore, this model has predicted attack points by applying test data and produced possible attack points for each attack at the 3rd time frame against the actual attack point. However, in the case of an Exploit attack, the consecutive overlapping attacks happen, there was ambiguity in the interpretation of the numerical values calculated by the LSTM. We presented a methodology for training data with binary values using LSTM and evaluation with RMSE metrics throughout this study.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/ACIS 6th International Conference on Big Data, Cloud Computing, and Data Science, BCD 2021
EditorsJixin Ma, Simon Xu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages53-59
Number of pages7
ISBN (Electronic)9781728176819
DOIs
StatePublished - Sep 13 2021
Event6th IEEE/ACIS International Conference on Big Data, Cloud Computing, and Data Science, BCD 2021 - Zhuhai, China
Duration: Sep 13 2021Sep 15 2021

Publication series

NameProceedings - 2021 IEEE/ACIS 6th International Conference on Big Data, Cloud Computing, and Data Science, BCD 2021

Conference

Conference6th IEEE/ACIS International Conference on Big Data, Cloud Computing, and Data Science, BCD 2021
Country/TerritoryChina
CityZhuhai
Period09/13/2109/15/21

Keywords

  • Anomaly-Based IDS
  • Big Data
  • LSTM
  • Machine Learning
  • RMSE

Fingerprint

Dive into the research topics of 'Intrusion Prediction using Long Short-Term Memory Deep Learning with UNSW-NB15'. Together they form a unique fingerprint.

Cite this