Towards trustworthy Artificial Intelligence: Security risk assessment methodology for Artificial Intelligence systems

Eider Iturbe; Erkuden Rios; Nerea Toledo

doi:10.1109/CloudCom59040.2023.00054

Towards trustworthy Artificial Intelligence: Security risk assessment methodology for Artificial Intelligence systems

Eider Iturbe^*
, Erkuden Rios
, Nerea Toledo

^*Corresponding author for this work

CIBERSEC and DLT

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

4 Citations (Scopus)

Abstract

The digitalization and smartization of modern digital systems include the implementation and integration of emerging innovative technologies, such as Artificial Intelligence. By incorporating new technologies, the surface attack of the system also expands, and specialized cybersecurity mechanisms and tools are required to counter the potential new threats. This paper introduces a holistic security risk assessment methodology that aims to assist Artificial Intelligence system stakeholders guarantee the correct design and implementation of technical robustness in Artificial Intelligence systems. The methodology is designed to facilitate the automation of the security risk assessment of Artificial Intelligence components together with the rest of the system components. Supporting the methodology, the solution to the automation of Artificial Intelligence risk assessment is also proposed. Both the methodology and the tool will be validated when assessing and treating risks on Artificial Intelligence-based cybersecurity solutions integrated in modern digital industrial systems that leverage emerging technologies such as cloud continuum including Software-defined networking (SDN).

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	291-297
Number of pages	7
ISBN (Electronic)	9798350339826
DOIs	https://doi.org/10.1109/CloudCom59040.2023.00054
Publication status	Published - 2023
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	4/12/23 → 6/12/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Keywords

Artificial Intelligence
Cyber Security
Risk Assessment
Technical robustness
Trustworthy

Access to Document

10.1109/CloudCom59040.2023.00054

Cite this

Iturbe, E., Rios, E., & Toledo, N. (2023). Towards trustworthy Artificial Intelligence: Security risk assessment methodology for Artificial Intelligence systems. In Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023 (pp. 291-297). (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom). IEEE Computer Society. https://doi.org/10.1109/CloudCom59040.2023.00054

Iturbe, Eider ; Rios, Erkuden ; Toledo, Nerea. / Towards trustworthy Artificial Intelligence : Security risk assessment methodology for Artificial Intelligence systems. Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023. IEEE Computer Society, 2023. pp. 291-297 (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom).

@inproceedings{12981551401a41529ccbf512420f2128,

title = "Towards trustworthy Artificial Intelligence: Security risk assessment methodology for Artificial Intelligence systems",

abstract = "The digitalization and smartization of modern digital systems include the implementation and integration of emerging innovative technologies, such as Artificial Intelligence. By incorporating new technologies, the surface attack of the system also expands, and specialized cybersecurity mechanisms and tools are required to counter the potential new threats. This paper introduces a holistic security risk assessment methodology that aims to assist Artificial Intelligence system stakeholders guarantee the correct design and implementation of technical robustness in Artificial Intelligence systems. The methodology is designed to facilitate the automation of the security risk assessment of Artificial Intelligence components together with the rest of the system components. Supporting the methodology, the solution to the automation of Artificial Intelligence risk assessment is also proposed. Both the methodology and the tool will be validated when assessing and treating risks on Artificial Intelligence-based cybersecurity solutions integrated in modern digital industrial systems that leverage emerging technologies such as cloud continuum including Software-defined networking (SDN).",

keywords = "Artificial Intelligence, Cyber Security, Risk Assessment, Technical robustness, Trustworthy",

author = "Eider Iturbe and Erkuden Rios and Nerea Toledo",

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/CloudCom59040.2023.00054",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "291--297",

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

address = "United States",

}

Iturbe, E , Rios, E & Toledo, N 2023, Towards trustworthy Artificial Intelligence: Security risk assessment methodology for Artificial Intelligence systems. 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. 291-297, 14th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023, Naples, Italy, 4/12/23. https://doi.org/10.1109/CloudCom59040.2023.00054

Towards trustworthy Artificial Intelligence: Security risk assessment methodology for Artificial Intelligence systems. / Iturbe, Eider ; Rios, Erkuden; Toledo, Nerea.
Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023. IEEE Computer Society, 2023. p. 291-297 (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom).

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

TY - GEN

T1 - Towards trustworthy Artificial Intelligence

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

AU - Iturbe, Eider

AU - Rios, Erkuden

AU - Toledo, Nerea

PY - 2023

Y1 - 2023

N2 - The digitalization and smartization of modern digital systems include the implementation and integration of emerging innovative technologies, such as Artificial Intelligence. By incorporating new technologies, the surface attack of the system also expands, and specialized cybersecurity mechanisms and tools are required to counter the potential new threats. This paper introduces a holistic security risk assessment methodology that aims to assist Artificial Intelligence system stakeholders guarantee the correct design and implementation of technical robustness in Artificial Intelligence systems. The methodology is designed to facilitate the automation of the security risk assessment of Artificial Intelligence components together with the rest of the system components. Supporting the methodology, the solution to the automation of Artificial Intelligence risk assessment is also proposed. Both the methodology and the tool will be validated when assessing and treating risks on Artificial Intelligence-based cybersecurity solutions integrated in modern digital industrial systems that leverage emerging technologies such as cloud continuum including Software-defined networking (SDN).

AB - The digitalization and smartization of modern digital systems include the implementation and integration of emerging innovative technologies, such as Artificial Intelligence. By incorporating new technologies, the surface attack of the system also expands, and specialized cybersecurity mechanisms and tools are required to counter the potential new threats. This paper introduces a holistic security risk assessment methodology that aims to assist Artificial Intelligence system stakeholders guarantee the correct design and implementation of technical robustness in Artificial Intelligence systems. The methodology is designed to facilitate the automation of the security risk assessment of Artificial Intelligence components together with the rest of the system components. Supporting the methodology, the solution to the automation of Artificial Intelligence risk assessment is also proposed. Both the methodology and the tool will be validated when assessing and treating risks on Artificial Intelligence-based cybersecurity solutions integrated in modern digital industrial systems that leverage emerging technologies such as cloud continuum including Software-defined networking (SDN).

KW - Artificial Intelligence

KW - Cyber Security

KW - Risk Assessment

KW - Technical robustness

KW - Trustworthy

UR - https://www.scopus.com/pages/publications/85189630361

U2 - 10.1109/CloudCom59040.2023.00054

DO - 10.1109/CloudCom59040.2023.00054

M3 - Conference contribution

AN - SCOPUS:85189630361

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

SP - 291

EP - 297

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

PB - IEEE Computer Society

Y2 - 4 December 2023 through 6 December 2023

ER -

Iturbe E , Rios E, Toledo N. Towards trustworthy Artificial Intelligence: Security risk assessment methodology for Artificial Intelligence systems. In Proceedings - 2023 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2023. IEEE Computer Society. 2023. p. 291-297. (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom). doi: 10.1109/CloudCom59040.2023.00054

Towards trustworthy Artificial Intelligence: Security risk assessment methodology for Artificial Intelligence systems

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this