An Evaluation of Transformer Models for Early Intrusion Detection in Cloud Continuum

Md Mahbub Islam; Tanwir Ahmad; Dragos Truscan

doi:10.1109/CloudCom59040.2023.00052

An Evaluation of Transformer Models for Early Intrusion Detection in Cloud Continuum

Md Mahbub Islam^*, Tanwir Ahmad, Dragos Truscan

^*Corresponding author for this work

Information Technology

Research output: Chapter in Book/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

With the increasing popularity of the cloud continuum, the security of different layers and nodes involved has become more relevant than ever. Intrusion detection systems, are one of the main tools to identify and intercept intrusion attacks. Furthermore, identifying the attacks in time, before they are completed, is necessary in order to deploy countermeasures in time and to limit the losses. In this work, we evaluate the use of transformer models for implementing early-detection signature-based detection systems targeted at Cloud Continuum. We implement the approach in the context of our tool for early detection of network intrusions and we evaluate it using the CICIDS2017 dataset and MQTT-IDS-2020. The results show that transformer models are a viable alternative for early-detection systems and this will pave the road for further research on the topic.

Original language	English
Title of host publication	Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023
Publisher	IEEE Computer Society
Pages	279-284
Number of pages	6
ISBN (Electronic)	9798350339826
DOIs	https://doi.org/10.1109/CloudCom59040.2023.00052
Publication status	Published - 2023
MoE publication type	A4 Article in a conference publication
Event	14th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023 - Naples, Italy Duration: 4 Dec 2023 → 6 Dec 2023

Publication series

Name	Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom
ISSN (Print)	2330-2194
ISSN (Electronic)	2330-2186

Conference

Conference	14th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023
Country/Territory	Italy
City	Naples
Period	04/12/23 → 06/12/23

Keywords

deep learning
Intrusion detection systems
monitoring
transformer-architecture

Access to Document

10.1109/CloudCom59040.2023.00052

Cite this

Islam, M. M., Ahmad, T., & Truscan, D. (2023). An Evaluation of Transformer Models for Early Intrusion Detection in Cloud Continuum. In Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023 (pp. 279-284). (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom). IEEE Computer Society. https://doi.org/10.1109/CloudCom59040.2023.00052

Islam, Md Mahbub ; Ahmad, Tanwir ; Truscan, Dragos. / An Evaluation of Transformer Models for Early Intrusion Detection in Cloud Continuum. Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023. IEEE Computer Society, 2023. pp. 279-284 (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom).

@inproceedings{4daa89c7025d4004b0f3444915e31a54,

title = "An Evaluation of Transformer Models for Early Intrusion Detection in Cloud Continuum",

abstract = "With the increasing popularity of the cloud continuum, the security of different layers and nodes involved has become more relevant than ever. Intrusion detection systems, are one of the main tools to identify and intercept intrusion attacks. Furthermore, identifying the attacks in time, before they are completed, is necessary in order to deploy countermeasures in time and to limit the losses. In this work, we evaluate the use of transformer models for implementing early-detection signature-based detection systems targeted at Cloud Continuum. We implement the approach in the context of our tool for early detection of network intrusions and we evaluate it using the CICIDS2017 dataset and MQTT-IDS-2020. The results show that transformer models are a viable alternative for early-detection systems and this will pave the road for further research on the topic.",

keywords = "deep learning, Intrusion detection systems, monitoring, transformer-architecture",

author = "Islam, {Md Mahbub} and Tanwir Ahmad and Dragos Truscan",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 14th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023 ; Conference date: 04-12-2023 Through 06-12-2023",

year = "2023",

doi = "10.1109/CloudCom59040.2023.00052",

language = "English",

series = "Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom",

publisher = "IEEE Computer Society",

pages = "279--284",

booktitle = "Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023",

}

Islam, MM , Ahmad, T & Truscan, D 2023, An Evaluation of Transformer Models for Early Intrusion Detection in Cloud Continuum. in Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023. Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom, IEEE Computer Society, pp. 279-284, 14th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023, Naples, Italy, 04/12/23. https://doi.org/10.1109/CloudCom59040.2023.00052

An Evaluation of Transformer Models for Early Intrusion Detection in Cloud Continuum. / Islam, Md Mahbub ; Ahmad, Tanwir ; Truscan, Dragos.
Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023. IEEE Computer Society, 2023. p. 279-284 (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom).

Research output: Chapter in Book/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - An Evaluation of Transformer Models for Early Intrusion Detection in Cloud Continuum

AU - Islam, Md Mahbub

AU - Ahmad, Tanwir

AU - Truscan, Dragos

PY - 2023

Y1 - 2023

N2 - With the increasing popularity of the cloud continuum, the security of different layers and nodes involved has become more relevant than ever. Intrusion detection systems, are one of the main tools to identify and intercept intrusion attacks. Furthermore, identifying the attacks in time, before they are completed, is necessary in order to deploy countermeasures in time and to limit the losses. In this work, we evaluate the use of transformer models for implementing early-detection signature-based detection systems targeted at Cloud Continuum. We implement the approach in the context of our tool for early detection of network intrusions and we evaluate it using the CICIDS2017 dataset and MQTT-IDS-2020. The results show that transformer models are a viable alternative for early-detection systems and this will pave the road for further research on the topic.

AB - With the increasing popularity of the cloud continuum, the security of different layers and nodes involved has become more relevant than ever. Intrusion detection systems, are one of the main tools to identify and intercept intrusion attacks. Furthermore, identifying the attacks in time, before they are completed, is necessary in order to deploy countermeasures in time and to limit the losses. In this work, we evaluate the use of transformer models for implementing early-detection signature-based detection systems targeted at Cloud Continuum. We implement the approach in the context of our tool for early detection of network intrusions and we evaluate it using the CICIDS2017 dataset and MQTT-IDS-2020. The results show that transformer models are a viable alternative for early-detection systems and this will pave the road for further research on the topic.

KW - deep learning

KW - Intrusion detection systems

KW - monitoring

KW - transformer-architecture

UR - http://www.scopus.com/inward/record.url?scp=85189648043&partnerID=8YFLogxK

U2 - 10.1109/CloudCom59040.2023.00052

DO - 10.1109/CloudCom59040.2023.00052

M3 - Conference contribution

AN - SCOPUS:85189648043

T3 - Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom

SP - 279

EP - 284

BT - Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023

PB - IEEE Computer Society

T2 - 14th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023

Y2 - 4 December 2023 through 6 December 2023

ER -

Islam MM , Ahmad T , Truscan D. An Evaluation of Transformer Models for Early Intrusion Detection in Cloud Continuum. In Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023. IEEE Computer Society. 2023. p. 279-284. (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom). doi: 10.1109/CloudCom59040.2023.00052

An Evaluation of Transformer Models for Early Intrusion Detection in Cloud Continuum

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

VeriDevOps: Automated Protection and Prevention to Meet Security Requirements in DevOps Environments

Cite this

An Evaluation of Transformer Models for Early Intrusion Detection in Cloud Continuum

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

VeriDevOps: Automated Protection and Prevention to Meet Security Requirements in DevOps Environments

Cite this