Risk-Aware Intrusion Detection and Prevention System for Automated UAS

Raphael Schermann; Thomas Ammerer; Philipp Stelzer; Georg MacHer; Christian Steger

doi:10.1109/ISSREW60843.2023.00065

Risk-Aware Intrusion Detection and Prevention System for Automated UAS

Raphael Schermann^*, Thomas Ammerer, Philipp Stelzer, Georg MacHer, Christian Steger

^*Korrespondierende/r Autor/-in für diese Arbeit

Institut für Technische Informatik (4480)

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Abstract

This paper designs a proof-of-concept for a Deep Learning-based IDS for UAS. As the drone market grows, safety becomes crucial. Unmanned Aircraft System (UAS) attacks can endanger lives and facilities. With the increasing complexity of attacks, detection has become challenging. Machine Learning-based Intrusion Detection System (IDS), trained on the CSE-CIC-IDS2018 dataset, can handle defined attacks. Combining IDS with an Intrusion Prevention System(IPS), using Threat Analysis and Risk Assessment (TARA) from the automotive domain ensures the system's safety even after attacks. The implementation involves Raspberry Pi as an attacker and defender. The ISO/SAE 21434 standard serves as the foundation for cybersecurity adaptation.

Originalsprache	englisch
Titel	Proceedings - 2023 IEEE 34th International Symposium on Software Reliability Engineering Workshop, ISSREW 2023
Herausgeber (Verlag)	Institute of Electrical and Electronics Engineers
Seiten	148-153
Seitenumfang	6
ISBN (elektronisch)	9798350319569
DOIs	https://doi.org/10.1109/ISSREW60843.2023.00065
Publikationsstatus	Veröffentlicht - 2023
Veranstaltung	34th IEEE International Symposium on Software Reliability Engineering Workshop: ISSREW 2023 - Florence, Italien Dauer: 9 Okt. 2023 → 12 Okt. 2023

Konferenz

Konferenz	34th IEEE International Symposium on Software Reliability Engineering Workshop
Kurztitel	ISSREW 2023
Land/Gebiet	Italien
Ort	Florence
Zeitraum	9/10/23 → 12/10/23

ASJC Scopus subject areas

Artificial intelligence
Software
Sicherheit, Risiko, Zuverlässigkeit und Qualität

Zugriff auf Dokument

10.1109/ISSREW60843.2023.00065

Andere Dateien und Links

Verknüpfung zur Publikation in Scopus

Dieses zitieren

Schermann, R., Ammerer, T., Stelzer, P., MacHer, G., & Steger, C. (2023). Risk-Aware Intrusion Detection and Prevention System for Automated UAS. in Proceedings - 2023 IEEE 34th International Symposium on Software Reliability Engineering Workshop, ISSREW 2023 (S. 148-153). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISSREW60843.2023.00065

Risk-Aware Intrusion Detection and Prevention System for Automated UAS. / Schermann, Raphael; Ammerer, Thomas; Stelzer, Philipp et al.
Proceedings - 2023 IEEE 34th International Symposium on Software Reliability Engineering Workshop, ISSREW 2023. Institute of Electrical and Electronics Engineers, 2023. S. 148-153.

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Schermann, R, Ammerer, T, Stelzer, P, MacHer, G & Steger, C 2023, Risk-Aware Intrusion Detection and Prevention System for Automated UAS. in Proceedings - 2023 IEEE 34th International Symposium on Software Reliability Engineering Workshop, ISSREW 2023. Institute of Electrical and Electronics Engineers, S. 148-153, 34th IEEE International Symposium on Software Reliability Engineering Workshop, Florence, Italien, 9/10/23. https://doi.org/10.1109/ISSREW60843.2023.00065

@inproceedings{cfaa0ed9835948c8bcf6350ca998ba91,

title = "Risk-Aware Intrusion Detection and Prevention System for Automated UAS",

abstract = "This paper designs a proof-of-concept for a Deep Learning-based IDS for UAS. As the drone market grows, safety becomes crucial. Unmanned Aircraft System (UAS) attacks can endanger lives and facilities. With the increasing complexity of attacks, detection has become challenging. Machine Learning-based Intrusion Detection System (IDS), trained on the CSE-CIC-IDS2018 dataset, can handle defined attacks. Combining IDS with an Intrusion Prevention System(IPS), using Threat Analysis and Risk Assessment (TARA) from the automotive domain ensures the system's safety even after attacks. The implementation involves Raspberry Pi as an attacker and defender. The ISO/SAE 21434 standard serves as the foundation for cybersecurity adaptation.",

keywords = "IDPS, safety, security, UAV",

author = "Raphael Schermann and Thomas Ammerer and Philipp Stelzer and Georg MacHer and Christian Steger",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 34th IEEE International Symposium on Software Reliability Engineering Workshop : ISSREW 2023, ISSREW 2023 ; Conference date: 09-10-2023 Through 12-10-2023",

year = "2023",

doi = "10.1109/ISSREW60843.2023.00065",

language = "English",

pages = "148--153",

booktitle = "Proceedings - 2023 IEEE 34th International Symposium on Software Reliability Engineering Workshop, ISSREW 2023",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

TY - GEN

T1 - Risk-Aware Intrusion Detection and Prevention System for Automated UAS

AU - Schermann, Raphael

AU - Ammerer, Thomas

AU - Stelzer, Philipp

AU - MacHer, Georg

AU - Steger, Christian

PY - 2023

Y1 - 2023

N2 - This paper designs a proof-of-concept for a Deep Learning-based IDS for UAS. As the drone market grows, safety becomes crucial. Unmanned Aircraft System (UAS) attacks can endanger lives and facilities. With the increasing complexity of attacks, detection has become challenging. Machine Learning-based Intrusion Detection System (IDS), trained on the CSE-CIC-IDS2018 dataset, can handle defined attacks. Combining IDS with an Intrusion Prevention System(IPS), using Threat Analysis and Risk Assessment (TARA) from the automotive domain ensures the system's safety even after attacks. The implementation involves Raspberry Pi as an attacker and defender. The ISO/SAE 21434 standard serves as the foundation for cybersecurity adaptation.

AB - This paper designs a proof-of-concept for a Deep Learning-based IDS for UAS. As the drone market grows, safety becomes crucial. Unmanned Aircraft System (UAS) attacks can endanger lives and facilities. With the increasing complexity of attacks, detection has become challenging. Machine Learning-based Intrusion Detection System (IDS), trained on the CSE-CIC-IDS2018 dataset, can handle defined attacks. Combining IDS with an Intrusion Prevention System(IPS), using Threat Analysis and Risk Assessment (TARA) from the automotive domain ensures the system's safety even after attacks. The implementation involves Raspberry Pi as an attacker and defender. The ISO/SAE 21434 standard serves as the foundation for cybersecurity adaptation.

KW - IDPS

KW - safety

KW - security

KW - UAV

UR - http://www.scopus.com/inward/record.url?scp=85178515791&partnerID=8YFLogxK

U2 - 10.1109/ISSREW60843.2023.00065

DO - 10.1109/ISSREW60843.2023.00065

M3 - Conference paper

AN - SCOPUS:85178515791

SP - 148

EP - 153

BT - Proceedings - 2023 IEEE 34th International Symposium on Software Reliability Engineering Workshop, ISSREW 2023

PB - Institute of Electrical and Electronics Engineers

T2 - 34th IEEE International Symposium on Software Reliability Engineering Workshop

Y2 - 9 October 2023 through 12 October 2023

ER -

Risk-Aware Intrusion Detection and Prevention System for Automated UAS

Abstract

Konferenz

ASJC Scopus subject areas

Zugriff auf Dokument

Andere Dateien und Links

Fingerprint

Dieses zitieren