A Technical Framework For Formally Verifying AI Models Supporting 6G Network Functions

M. M.Hassan Mahmud; Renjith Baby; Shadi Moazzeni; Juan Parra-Ullauri; Xueqing Zhou; Yulei Wu; Konstantinos Katsaros; Ioannis Mavromatis; Shah Zeb; Rasheed Hussain; Dimitra Simeonidou

doi:10.1109/INFOCOMWKSHPS65812.2025.11152991

A Technical Framework For Formally Verifying AI Models Supporting 6G Network Functions

M. M.Hassan Mahmud^*, Renjith Baby, Shadi Moazzeni, Juan Parra-Ullauri, Xueqing Zhou, Yulei Wu, Konstantinos Katsaros, Ioannis Mavromatis, Shah Zeb, Rasheed Hussain, Dimitra Simeonidou

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

1 Downloads (Pure)

Abstract

In this paper we propose a technical framework for applying formally verifiable AI (FVAI) methods to certify AI models that support 6G network functions. The certifications state that the input/output behavior of an AI model conforms to a specification or identifies potential issues with the model. This paper contributes to the broad spectrum of methods necessary to ensure that deep learning models, known to have instability issues, are sufficiently trustworthy for supporting functions in critical infrastructure like 6G networks. The proposed framework gives a unified way of representing network functions supported by AI models, certifications, construction of those certifications from model behaviour, and incorporating technical tools for bounding AI model input/output behaviour. We also illustrate the use of this framework in verifying AI models in two 6G use cases on optimisations in virtual network functions and radio access network resources. Furthermore, we discuss how this framework can be extended in the future.

Original language	English
Title of host publication	IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	6
ISBN (Electronic)	9798331543709
ISBN (Print)	9798331543716
DOIs	https://doi.org/10.1109/INFOCOMWKSHPS65812.2025.11152991
Publication status	Published - 12 Sept 2025
Event	2025 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025 - London, United Kingdom Duration: 19 May 2025 → 19 May 2025 https://infocom2025.ieee-infocom.org/

Publication series

Name	IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025
ISSN (Print)	2159-4228
ISSN (Electronic)	2833-0587

Conference

Conference	2025 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025
Country/Territory	United Kingdom
City	London
Period	19/05/25 → 19/05/25
Internet address	https://infocom2025.ieee-infocom.org/

Bibliographical note

Publisher Copyright:
© 2025 IEEE.

Keywords

6G
Artificial Intelligence
Formally Verified AI
mATRIC
Network Function Virtualisation
Trustworthy AI

Access to Document

10.1109/INFOCOMWKSHPS65812.2025.11152991

Full-text PDF (accepted manuscript)
This is the accepted author manuscript (AAM) of the article which has been made Open Access under the University of Bristol's Scholarly Works Policy. The final published version (Version of Record) can be found on the publisher's website. The copyright of any third-party content, such as images, remains with the copyright holder.
Accepted author manuscript, 702 KBLicence: CC BY

Handle.net

Persistent link

Cite this

Mahmud, M. M. H., Baby, R., Moazzeni, S., Parra-Ullauri, J., Zhou, X., Wu, Y., Katsaros, K., Mavromatis, I., Zeb, S., Hussain, R., & Simeonidou, D. (2025). A Technical Framework For Formally Verifying AI Models Supporting 6G Network Functions. In IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025 (IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/INFOCOMWKSHPS65812.2025.11152991

@inproceedings{7a9de782bc5c447b8436839600d5a11b,

title = "A Technical Framework For Formally Verifying AI Models Supporting 6G Network Functions",

abstract = "In this paper we propose a technical framework for applying formally verifiable AI (FVAI) methods to certify AI models that support 6G network functions. The certifications state that the input/output behavior of an AI model conforms to a specification or identifies potential issues with the model. This paper contributes to the broad spectrum of methods necessary to ensure that deep learning models, known to have instability issues, are sufficiently trustworthy for supporting functions in critical infrastructure like 6G networks. The proposed framework gives a unified way of representing network functions supported by AI models, certifications, construction of those certifications from model behaviour, and incorporating technical tools for bounding AI model input/output behaviour. We also illustrate the use of this framework in verifying AI models in two 6G use cases on optimisations in virtual network functions and radio access network resources. Furthermore, we discuss how this framework can be extended in the future.",

keywords = "6G, Artificial Intelligence, Formally Verified AI, mATRIC, Network Function Virtualisation, Trustworthy AI",

author = "Mahmud, \{M. M.Hassan\} and Renjith Baby and Shadi Moazzeni and Juan Parra-Ullauri and Xueqing Zhou and Yulei Wu and Konstantinos Katsaros and Ioannis Mavromatis and Shah Zeb and Rasheed Hussain and Dimitra Simeonidou",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025 ; Conference date: 19-05-2025 Through 19-05-2025",

year = "2025",

month = sep,

day = "12",

doi = "10.1109/INFOCOMWKSHPS65812.2025.11152991",

language = "English",

isbn = "9798331543716",

series = "IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

booktitle = "IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025",

address = "United States",

url = "https://infocom2025.ieee-infocom.org/",

}

Mahmud, MMH, Baby, R, Moazzeni, S, Parra-Ullauri, J, Zhou, X , Wu, Y, Katsaros, K, Mavromatis, I, Zeb, S, Hussain, R & Simeonidou, D 2025, A Technical Framework For Formally Verifying AI Models Supporting 6G Network Functions. in IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025. IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025, Institute of Electrical and Electronics Engineers (IEEE), 2025 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025, London, United Kingdom, 19/05/25. https://doi.org/10.1109/INFOCOMWKSHPS65812.2025.11152991

A Technical Framework For Formally Verifying AI Models Supporting 6G Network Functions. / Mahmud, M. M.Hassan; Baby, Renjith; Moazzeni, Shadi et al.
IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025. Institute of Electrical and Electronics Engineers (IEEE), 2025. (IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - A Technical Framework For Formally Verifying AI Models Supporting 6G Network Functions

AU - Mahmud, M. M.Hassan

AU - Baby, Renjith

AU - Moazzeni, Shadi

AU - Parra-Ullauri, Juan

AU - Zhou, Xueqing

AU - Wu, Yulei

AU - Katsaros, Konstantinos

AU - Mavromatis, Ioannis

AU - Zeb, Shah

AU - Hussain, Rasheed

AU - Simeonidou, Dimitra

PY - 2025/9/12

Y1 - 2025/9/12

N2 - In this paper we propose a technical framework for applying formally verifiable AI (FVAI) methods to certify AI models that support 6G network functions. The certifications state that the input/output behavior of an AI model conforms to a specification or identifies potential issues with the model. This paper contributes to the broad spectrum of methods necessary to ensure that deep learning models, known to have instability issues, are sufficiently trustworthy for supporting functions in critical infrastructure like 6G networks. The proposed framework gives a unified way of representing network functions supported by AI models, certifications, construction of those certifications from model behaviour, and incorporating technical tools for bounding AI model input/output behaviour. We also illustrate the use of this framework in verifying AI models in two 6G use cases on optimisations in virtual network functions and radio access network resources. Furthermore, we discuss how this framework can be extended in the future.

AB - In this paper we propose a technical framework for applying formally verifiable AI (FVAI) methods to certify AI models that support 6G network functions. The certifications state that the input/output behavior of an AI model conforms to a specification or identifies potential issues with the model. This paper contributes to the broad spectrum of methods necessary to ensure that deep learning models, known to have instability issues, are sufficiently trustworthy for supporting functions in critical infrastructure like 6G networks. The proposed framework gives a unified way of representing network functions supported by AI models, certifications, construction of those certifications from model behaviour, and incorporating technical tools for bounding AI model input/output behaviour. We also illustrate the use of this framework in verifying AI models in two 6G use cases on optimisations in virtual network functions and radio access network resources. Furthermore, we discuss how this framework can be extended in the future.

KW - 6G

KW - Artificial Intelligence

KW - Formally Verified AI

KW - mATRIC

KW - Network Function Virtualisation

KW - Trustworthy AI

U2 - 10.1109/INFOCOMWKSHPS65812.2025.11152991

DO - 10.1109/INFOCOMWKSHPS65812.2025.11152991

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:105017967338

SN - 9798331543716

T3 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025

BT - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2025 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025

Y2 - 19 May 2025 through 19 May 2025

ER -

Mahmud MMH, Baby R, Moazzeni S, Parra-Ullauri J, Zhou X , Wu Y et al. A Technical Framework For Formally Verifying AI Models Supporting 6G Network Functions. In IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025. Institute of Electrical and Electronics Engineers (IEEE). 2025. (IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025). doi: 10.1109/INFOCOMWKSHPS65812.2025.11152991

A Technical Framework For Formally Verifying AI Models Supporting 6G Network Functions

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Handle.net

Fingerprint

Cite this