Adaptive database intrusion detection using evolutionary reinforcement learning

Seul Gi Choi, Sung-Bae Cho

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes an adaptive database intrusion detection model that can be resistant to potential insider misuse with a limited number of data. The intrusion detection model can be adapted online using evolutionary reinforcement learning (ERL) which combines reinforcement learning and evolutionary learning. The model consists of two feedforward neural networks, a behavior network and an evaluation network. The behavior network detects the intrusion, and the evaluation network provides feedback to the detection of the behavior network. To find the optimal model, we encode the weights of the networks as an individual and produce populations of better individuals over generations. TPC-E scenario-based virtual query data were used for verification of the proposed model. Experimental results show that the detection performance improves as the proposed model learns the intrusion adaptively.

Original languageEnglish
Title of host publicationInternational Joint Conference SOCO’17- CISIS’17-ICEUTE’17, Proceedings
EditorsHilde Perez Garcia, Javier Alfonso-Cendon, Lidia Sanchez Gonzalez, Emilio Corchado, Hector Quintian
PublisherSpringer Verlag
Pages547-556
Number of pages10
ISBN (Print)9783319671796
DOIs
Publication statusPublished - 2018 Jan 1
EventInternational Joint Conference on 12th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2017, 10th International Conference on Computational Intelligence in Security for Information Systems, CISIS 2017 and 8th International Conference on European Transnational Education, ICEUTE 2017 - Leon, Spain
Duration: 2017 Sep 62017 Sep 8

Publication series

NameAdvances in Intelligent Systems and Computing
Volume649
ISSN (Print)2194-5357

Other

OtherInternational Joint Conference on 12th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2017, 10th International Conference on Computational Intelligence in Security for Information Systems, CISIS 2017 and 8th International Conference on European Transnational Education, ICEUTE 2017
CountrySpain
CityLeon
Period17/9/617/9/8

Fingerprint

Reinforcement learning
Intrusion detection
Feedforward neural networks
Feedback

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Choi, S. G., & Cho, S-B. (2018). Adaptive database intrusion detection using evolutionary reinforcement learning. In H. Perez Garcia, J. Alfonso-Cendon, L. Sanchez Gonzalez, E. Corchado, & H. Quintian (Eds.), International Joint Conference SOCO’17- CISIS’17-ICEUTE’17, Proceedings (pp. 547-556). (Advances in Intelligent Systems and Computing; Vol. 649). Springer Verlag. https://doi.org/10.1007/978-3-319-67180-2_53
Choi, Seul Gi ; Cho, Sung-Bae. / Adaptive database intrusion detection using evolutionary reinforcement learning. International Joint Conference SOCO’17- CISIS’17-ICEUTE’17, Proceedings. editor / Hilde Perez Garcia ; Javier Alfonso-Cendon ; Lidia Sanchez Gonzalez ; Emilio Corchado ; Hector Quintian. Springer Verlag, 2018. pp. 547-556 (Advances in Intelligent Systems and Computing).
@inproceedings{9df37cfe6d594185bb5933773978262a,
title = "Adaptive database intrusion detection using evolutionary reinforcement learning",
abstract = "This paper proposes an adaptive database intrusion detection model that can be resistant to potential insider misuse with a limited number of data. The intrusion detection model can be adapted online using evolutionary reinforcement learning (ERL) which combines reinforcement learning and evolutionary learning. The model consists of two feedforward neural networks, a behavior network and an evaluation network. The behavior network detects the intrusion, and the evaluation network provides feedback to the detection of the behavior network. To find the optimal model, we encode the weights of the networks as an individual and produce populations of better individuals over generations. TPC-E scenario-based virtual query data were used for verification of the proposed model. Experimental results show that the detection performance improves as the proposed model learns the intrusion adaptively.",
author = "Choi, {Seul Gi} and Sung-Bae Cho",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-3-319-67180-2_53",
language = "English",
isbn = "9783319671796",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "547--556",
editor = "{Perez Garcia}, Hilde and Javier Alfonso-Cendon and {Sanchez Gonzalez}, Lidia and Emilio Corchado and Hector Quintian",
booktitle = "International Joint Conference SOCO’17- CISIS’17-ICEUTE’17, Proceedings",
address = "Germany",

}

Choi, SG & Cho, S-B 2018, Adaptive database intrusion detection using evolutionary reinforcement learning. in H Perez Garcia, J Alfonso-Cendon, L Sanchez Gonzalez, E Corchado & H Quintian (eds), International Joint Conference SOCO’17- CISIS’17-ICEUTE’17, Proceedings. Advances in Intelligent Systems and Computing, vol. 649, Springer Verlag, pp. 547-556, International Joint Conference on 12th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2017, 10th International Conference on Computational Intelligence in Security for Information Systems, CISIS 2017 and 8th International Conference on European Transnational Education, ICEUTE 2017, Leon, Spain, 17/9/6. https://doi.org/10.1007/978-3-319-67180-2_53

Adaptive database intrusion detection using evolutionary reinforcement learning. / Choi, Seul Gi; Cho, Sung-Bae.

International Joint Conference SOCO’17- CISIS’17-ICEUTE’17, Proceedings. ed. / Hilde Perez Garcia; Javier Alfonso-Cendon; Lidia Sanchez Gonzalez; Emilio Corchado; Hector Quintian. Springer Verlag, 2018. p. 547-556 (Advances in Intelligent Systems and Computing; Vol. 649).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Adaptive database intrusion detection using evolutionary reinforcement learning

AU - Choi, Seul Gi

AU - Cho, Sung-Bae

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This paper proposes an adaptive database intrusion detection model that can be resistant to potential insider misuse with a limited number of data. The intrusion detection model can be adapted online using evolutionary reinforcement learning (ERL) which combines reinforcement learning and evolutionary learning. The model consists of two feedforward neural networks, a behavior network and an evaluation network. The behavior network detects the intrusion, and the evaluation network provides feedback to the detection of the behavior network. To find the optimal model, we encode the weights of the networks as an individual and produce populations of better individuals over generations. TPC-E scenario-based virtual query data were used for verification of the proposed model. Experimental results show that the detection performance improves as the proposed model learns the intrusion adaptively.

AB - This paper proposes an adaptive database intrusion detection model that can be resistant to potential insider misuse with a limited number of data. The intrusion detection model can be adapted online using evolutionary reinforcement learning (ERL) which combines reinforcement learning and evolutionary learning. The model consists of two feedforward neural networks, a behavior network and an evaluation network. The behavior network detects the intrusion, and the evaluation network provides feedback to the detection of the behavior network. To find the optimal model, we encode the weights of the networks as an individual and produce populations of better individuals over generations. TPC-E scenario-based virtual query data were used for verification of the proposed model. Experimental results show that the detection performance improves as the proposed model learns the intrusion adaptively.

UR - http://www.scopus.com/inward/record.url?scp=85028667927&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028667927&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-67180-2_53

DO - 10.1007/978-3-319-67180-2_53

M3 - Conference contribution

SN - 9783319671796

T3 - Advances in Intelligent Systems and Computing

SP - 547

EP - 556

BT - International Joint Conference SOCO’17- CISIS’17-ICEUTE’17, Proceedings

A2 - Perez Garcia, Hilde

A2 - Alfonso-Cendon, Javier

A2 - Sanchez Gonzalez, Lidia

A2 - Corchado, Emilio

A2 - Quintian, Hector

PB - Springer Verlag

ER -

Choi SG, Cho S-B. Adaptive database intrusion detection using evolutionary reinforcement learning. In Perez Garcia H, Alfonso-Cendon J, Sanchez Gonzalez L, Corchado E, Quintian H, editors, International Joint Conference SOCO’17- CISIS’17-ICEUTE’17, Proceedings. Springer Verlag. 2018. p. 547-556. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-67180-2_53