RIN: Towards a Semantic Rigorous Interpretable Artificial Immune System for Intrusion Detection

Qianru Zhou; Rongzhen Li; Lei Xu; Anmin Fu; Jian Yang; Alasdair J. G. Gray; Stephen McLaughlin

doi:10.1007/978-3-031-27609-5_17

RIN: Towards a Semantic Rigorous Interpretable Artificial Immune System for Intrusion Detection

Qianru Zhou^*, Rongzhen Li, Lei Xu, Anmin Fu, Jian Yang, Alasdair J. G. Gray, Stephen McLaughlin

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The Internet is the most complex machine humankind has ever built, and how to defense it from intrusions is even more complex. With the ever increasing of new intrusions, intrusion detection task rely on Artificial Intelligence more and more. Interpretability and transparency of the machine learning model is the foundation of trust in AI-driven intrusion detection results. Current interpretation Artificial Intelligence technologies in intrusion detection are heuristic, which is neither accurate nor sufficient. This paper proposed a rigorous interpretable Artificial Intelligence driven intrusion detection approach, based on formal logic calculations. Details of rigorous interpretation calculation process for a decision tree model is presented. Prime implicant explanation for benign traffic flow are given in detail as rule for negative selection of the cyber immune system. Experiments are carried out in real-life traffic.

Original language	English
Title of host publication	Soft Computing and Its Engineering Applications. icSoftComp 2022
Editors	Kanubhai K. Patel, Atul Patel, K. C. Santosh, Ashish Ghosh
Publisher	Springer
Pages	213-224
Number of pages	12
ISBN (Electronic)	9783031276095
ISBN (Print)	9783031276088
DOIs	https://doi.org/10.1007/978-3-031-27609-5_17
Publication status	Published - 8 Mar 2023
Event	4th International Conference on Soft Computing and its Engineering Applications 2022 - Anand, India Duration: 9 Dec 2022 → 10 Dec 2022

Publication series

Name	Communications in Computer and Information Science
Volume	1788
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	4th International Conference on Soft Computing and its Engineering Applications 2022
Abbreviated title	icSoftComp 2022
Country/Territory	India
City	Anand
Period	9/12/22 → 10/12/22

Keywords

Artificial immune system
Explainable artificial intelligence
Interpretable machine learning
Intrusion detection
Prime implicant

ASJC Scopus subject areas

General Computer Science
General Mathematics

Access to Document

10.1007/978-3-031-27609-5_17

Cite this

Zhou, Q., Li, R., Xu, L., Fu, A., Yang, J., Gray, A. J. G., & McLaughlin, S. (2023). RIN: Towards a Semantic Rigorous Interpretable Artificial Immune System for Intrusion Detection. In K. K. Patel, A. Patel, K. C. Santosh, & A. Ghosh (Eds.), Soft Computing and Its Engineering Applications. icSoftComp 2022 (pp. 213-224). (Communications in Computer and Information Science; Vol. 1788). Springer. https://doi.org/10.1007/978-3-031-27609-5_17

@inproceedings{c8a1f1b395be490fbe89fbee955941f2,

title = "RIN: Towards a Semantic Rigorous Interpretable Artificial Immune System for Intrusion Detection",

abstract = "The Internet is the most complex machine humankind has ever built, and how to defense it from intrusions is even more complex. With the ever increasing of new intrusions, intrusion detection task rely on Artificial Intelligence more and more. Interpretability and transparency of the machine learning model is the foundation of trust in AI-driven intrusion detection results. Current interpretation Artificial Intelligence technologies in intrusion detection are heuristic, which is neither accurate nor sufficient. This paper proposed a rigorous interpretable Artificial Intelligence driven intrusion detection approach, based on formal logic calculations. Details of rigorous interpretation calculation process for a decision tree model is presented. Prime implicant explanation for benign traffic flow are given in detail as rule for negative selection of the cyber immune system. Experiments are carried out in real-life traffic.",

keywords = "Artificial immune system, Explainable artificial intelligence, Interpretable machine learning, Intrusion detection, Prime implicant",

author = "Qianru Zhou and Rongzhen Li and Lei Xu and Anmin Fu and Jian Yang and Gray, {Alasdair J. G.} and Stephen McLaughlin",

note = "Funding Information: Acknowledgments. This work is supported by the Starting Program of Nanjing University of Science and Technology (No. AE89991/324), the Science and Technology Program of STATE GRID Corporation of China (5200-202140365A), the National Natural Science Foundation of China (No. 61973161, 61991404), and Jiangsu Science and technology planning project (No. be2021610). Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 4th International Conference on Soft Computing and its Engineering Applications 2022, icSoftComp 2022 ; Conference date: 09-12-2022 Through 10-12-2022",

year = "2023",

month = mar,

day = "8",

doi = "10.1007/978-3-031-27609-5_17",

language = "English",

isbn = "9783031276088",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "213--224",

editor = "Patel, {Kanubhai K.} and Atul Patel and Santosh, {K. C.} and Ashish Ghosh",

booktitle = "Soft Computing and Its Engineering Applications. icSoftComp 2022",

}

Zhou, Q, Li, R, Xu, L, Fu, A, Yang, J, Gray, AJG & McLaughlin, S 2023, RIN: Towards a Semantic Rigorous Interpretable Artificial Immune System for Intrusion Detection. in KK Patel, A Patel, KC Santosh & A Ghosh (eds), Soft Computing and Its Engineering Applications. icSoftComp 2022. Communications in Computer and Information Science, vol. 1788, Springer, pp. 213-224, 4th International Conference on Soft Computing and its Engineering Applications 2022, Anand, India, 9/12/22. https://doi.org/10.1007/978-3-031-27609-5_17

RIN: Towards a Semantic Rigorous Interpretable Artificial Immune System for Intrusion Detection. / Zhou, Qianru; Li, Rongzhen; Xu, Lei et al.
Soft Computing and Its Engineering Applications. icSoftComp 2022. ed. / Kanubhai K. Patel; Atul Patel; K. C. Santosh; Ashish Ghosh. Springer, 2023. p. 213-224 (Communications in Computer and Information Science; Vol. 1788).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - RIN

T2 - 4th International Conference on Soft Computing and its Engineering Applications 2022

AU - Zhou, Qianru

AU - Li, Rongzhen

AU - Xu, Lei

AU - Fu, Anmin

AU - Yang, Jian

AU - Gray, Alasdair J. G.

AU - McLaughlin, Stephen

N1 - Funding Information: Acknowledgments. This work is supported by the Starting Program of Nanjing University of Science and Technology (No. AE89991/324), the Science and Technology Program of STATE GRID Corporation of China (5200-202140365A), the National Natural Science Foundation of China (No. 61973161, 61991404), and Jiangsu Science and technology planning project (No. be2021610). Publisher Copyright: © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2023/3/8

Y1 - 2023/3/8

N2 - The Internet is the most complex machine humankind has ever built, and how to defense it from intrusions is even more complex. With the ever increasing of new intrusions, intrusion detection task rely on Artificial Intelligence more and more. Interpretability and transparency of the machine learning model is the foundation of trust in AI-driven intrusion detection results. Current interpretation Artificial Intelligence technologies in intrusion detection are heuristic, which is neither accurate nor sufficient. This paper proposed a rigorous interpretable Artificial Intelligence driven intrusion detection approach, based on formal logic calculations. Details of rigorous interpretation calculation process for a decision tree model is presented. Prime implicant explanation for benign traffic flow are given in detail as rule for negative selection of the cyber immune system. Experiments are carried out in real-life traffic.

AB - The Internet is the most complex machine humankind has ever built, and how to defense it from intrusions is even more complex. With the ever increasing of new intrusions, intrusion detection task rely on Artificial Intelligence more and more. Interpretability and transparency of the machine learning model is the foundation of trust in AI-driven intrusion detection results. Current interpretation Artificial Intelligence technologies in intrusion detection are heuristic, which is neither accurate nor sufficient. This paper proposed a rigorous interpretable Artificial Intelligence driven intrusion detection approach, based on formal logic calculations. Details of rigorous interpretation calculation process for a decision tree model is presented. Prime implicant explanation for benign traffic flow are given in detail as rule for negative selection of the cyber immune system. Experiments are carried out in real-life traffic.

KW - Artificial immune system

KW - Explainable artificial intelligence

KW - Interpretable machine learning

KW - Intrusion detection

KW - Prime implicant

UR - http://www.scopus.com/inward/record.url?scp=85151060111&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-27609-5_17

DO - 10.1007/978-3-031-27609-5_17

M3 - Conference contribution

AN - SCOPUS:85151060111

SN - 9783031276088

T3 - Communications in Computer and Information Science

SP - 213

EP - 224

BT - Soft Computing and Its Engineering Applications. icSoftComp 2022

A2 - Patel, Kanubhai K.

A2 - Patel, Atul

A2 - Santosh, K. C.

A2 - Ghosh, Ashish

PB - Springer

Y2 - 9 December 2022 through 10 December 2022

ER -

Zhou Q, Li R, Xu L, Fu A, Yang J, Gray AJG et al. RIN: Towards a Semantic Rigorous Interpretable Artificial Immune System for Intrusion Detection. In Patel KK, Patel A, Santosh KC, Ghosh A, editors, Soft Computing and Its Engineering Applications. icSoftComp 2022. Springer. 2023. p. 213-224. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-27609-5_17