Real-time detection of TOR attacks from the Dark Web

Selahattin Hurol Turen; Kenneth Eustace; Rafiqul Islam; Geoffrey Fellows

doi:10.1007/978-3-031-14054-9_32

Real-time detection of TOR attacks from the Dark Web

Selahattin Hurol Turen, Kenneth Eustace, Rafiqul Islam, Geoffrey Fellows

Research output: Book chapter/Published conference paper › Conference paper › peer-review

Abstract

This paper discusses a case study project in cybersecurity on the Dark Web that uses quantitative data science research methods and techniques. Beginning with a comparative analysis of dark web forum data sets using data science techniques and then adding an experimental research design that includes machine learning techniques and strategies for training and development of a model.

After the gap analysis was identified from an extensive literature review, the authors suggest that it is possible to try to extend or modify these algorithms or the applied techniques. This hybrid experimental research methodology will lead to a proposal on mitigating risks via a model for real-time detection, evaluation, and response by cybersecurity professionals.

Original language	English
Title of host publication	Proceedings of the ICR’22 International Conference on Innovations in Computing Research
Editors	K Daimi, A Al Sadoon
Place of Publication	Cham, Switzerland
Publisher	Springer
Pages	346-355
Number of pages	10
Volume	1431
ISBN (Electronic)	9783031140549
ISBN (Print)	9783031140532
DOIs	https://doi.org/10.1007/978-3-031-14054-9_32
Publication status	Published - Nov 2022
Event	2022 International Conference on Innovations in Computing Research: ICR'22 - Novotel Hotel, Athens, Greece Duration: 29 Aug 2022 → 31 Aug 2022 https://iicser.org/icr22/ (Conference website) https://link.springer.com/book/10.1007/978-3-031-14054-9 (Proceedings)

Conference

Conference	2022 International Conference on Innovations in Computing Research
Country/Territory	Greece
City	Athens
Period	29/08/22 → 31/08/22
Other	The 2022 International Conference on Innovations in Computing Research (ICR’22) will be composed of research paper presentations, keynote speeches, panels, special sessions, workshops and tutorials. All accepted and registered papers will be published in the conference Proceedings and indexed. The Proceedings will be published by Springer book series: Advances in Intelligent Systems and Computing, and indexed by DBLP, INSPEC, WTI Frankfurt eG, zbMATH, and Japanese Science and Technology Agency (JST).
Internet address	https://iicser.org/icr22/ (Conference website) https://link.springer.com/book/10.1007/978-3-031-14054-9 (Proceedings)

Access to Document

10.1007/978-3-031-14054-9_32

Cite this

@inproceedings{97b6543b8d03470a892df4fb19884300,

title = "Real-time detection of TOR attacks from the Dark Web",

abstract = "This paper discusses a case study project in cybersecurity on the Dark Web that uses quantitative data science research methods and techniques. Beginning with a comparative analysis of dark web forum data sets using data science techniques and then adding an experimental research design that includes machine learning techniques and strategies for training and development of a model.After the gap analysis was identified from an extensive literature review, the authors suggest that it is possible to try to extend or modify these algorithms or the applied techniques. This hybrid experimental research methodology will lead to a proposal on mitigating risks via a model for real-time detection, evaluation, and response by cybersecurity professionals.",

keywords = "Dark web, Threat analytics, Machine learning algorithms, Real-time detection, Hybrid experimental research",

author = "Turen, {Selahattin Hurol} and Kenneth Eustace and Rafiqul Islam and Geoffrey Fellows",

year = "2022",

month = nov,

doi = "10.1007/978-3-031-14054-9_32",

language = "English",

isbn = "9783031140532",

volume = "1431",

pages = "346--355",

editor = "K Daimi and {Al Sadoon}, A",

booktitle = "Proceedings of the ICR{\textquoteright}22 International Conference on Innovations in Computing Research",

publisher = "Springer",

address = "United States",

note = "2022 International Conference on Innovations in Computing Research : ICR'22 ; Conference date: 29-08-2022 Through 31-08-2022",

url = "https://iicser.org/icr22/, https://link.springer.com/book/10.1007/978-3-031-14054-9",

}

Turen, SH, Eustace, K , Islam, R & Fellows, G 2022, Real-time detection of TOR attacks from the Dark Web. in K Daimi & A Al Sadoon (eds), Proceedings of the ICR’22 International Conference on Innovations in Computing Research. vol. 1431, Springer, Cham, Switzerland, pp. 346-355, 2022 International Conference on Innovations in Computing Research, Athens, Greece, 29/08/22. https://doi.org/10.1007/978-3-031-14054-9_32

Real-time detection of TOR attacks from the Dark Web. / Turen, Selahattin Hurol; Eustace, Kenneth ; Islam, Rafiqul et al.
Proceedings of the ICR’22 International Conference on Innovations in Computing Research. ed. / K Daimi; A Al Sadoon. Vol. 1431 Cham, Switzerland: Springer, 2022. p. 346-355.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Real-time detection of TOR attacks from the Dark Web

AU - Turen, Selahattin Hurol

AU - Eustace, Kenneth

AU - Islam, Rafiqul

AU - Fellows, Geoffrey

PY - 2022/11

Y1 - 2022/11

N2 - This paper discusses a case study project in cybersecurity on the Dark Web that uses quantitative data science research methods and techniques. Beginning with a comparative analysis of dark web forum data sets using data science techniques and then adding an experimental research design that includes machine learning techniques and strategies for training and development of a model.After the gap analysis was identified from an extensive literature review, the authors suggest that it is possible to try to extend or modify these algorithms or the applied techniques. This hybrid experimental research methodology will lead to a proposal on mitigating risks via a model for real-time detection, evaluation, and response by cybersecurity professionals.

AB - This paper discusses a case study project in cybersecurity on the Dark Web that uses quantitative data science research methods and techniques. Beginning with a comparative analysis of dark web forum data sets using data science techniques and then adding an experimental research design that includes machine learning techniques and strategies for training and development of a model.After the gap analysis was identified from an extensive literature review, the authors suggest that it is possible to try to extend or modify these algorithms or the applied techniques. This hybrid experimental research methodology will lead to a proposal on mitigating risks via a model for real-time detection, evaluation, and response by cybersecurity professionals.

KW - Dark web

KW - Threat analytics

KW - Machine learning algorithms

KW - Real-time detection

KW - Hybrid experimental research

UR - https://rdcu.be/dVJ7d

U2 - 10.1007/978-3-031-14054-9_32

DO - 10.1007/978-3-031-14054-9_32

M3 - Conference paper

SN - 9783031140532

VL - 1431

SP - 346

EP - 355

BT - Proceedings of the ICR’22 International Conference on Innovations in Computing Research

A2 - Daimi, K

A2 - Al Sadoon, A

PB - Springer

CY - Cham, Switzerland

T2 - 2022 International Conference on Innovations in Computing Research

Y2 - 29 August 2022 through 31 August 2022

ER -

Real-time detection of TOR attacks from the Dark Web

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this