On Assessing Vulnerabilities of the 5G Networks to Adversarial Examples
The use of artificial intelligence and machine learning is recognized as the key enabler for 5G mobile networks which would allow service providers to tackle the network complexity and ensure security, reliability and allocation of the necessary resources to their customers in a dynamic, robust and...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9968009/ |
_version_ | 1811185093565218816 |
---|---|
author | Mikhail Zolotukhin Parsa Miraghaei Di Zhang Timo Hamalainen |
author_facet | Mikhail Zolotukhin Parsa Miraghaei Di Zhang Timo Hamalainen |
author_sort | Mikhail Zolotukhin |
collection | DOAJ |
description | The use of artificial intelligence and machine learning is recognized as the key enabler for 5G mobile networks which would allow service providers to tackle the network complexity and ensure security, reliability and allocation of the necessary resources to their customers in a dynamic, robust and trustworthy way. Dependability of the future generation networks on accurate and timely performance of its artificial intelligence components means that disturbance in the functionality of these components may have negative impact on the entire network. As a result, there is an increasing concern about the vulnerability of intelligent machine learning driven frameworks to adversarial effects. In this study, we evaluate various adversarial example generation attacks against multiple artificial intelligence and machine learning models which can potentially be deployed in future 5G networks. First, we describe multiple use cases for which attacks on machine learning components are conceivable including the models employed and the data used for their training. After that, attack algorithms, their implementations and adjustments to the target models are summarised. Finally, the attacks implemented for the aforementioned use cases are evaluated based on deterioration of the objective functions optimised by the target models. |
first_indexed | 2024-04-11T13:24:52Z |
format | Article |
id | doaj.art-82c38f81024a442e8f9484167582e6a5 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-11T13:24:52Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-82c38f81024a442e8f9484167582e6a52022-12-22T04:22:07ZengIEEEIEEE Access2169-35362022-01-011012628512630310.1109/ACCESS.2022.32259219968009On Assessing Vulnerabilities of the 5G Networks to Adversarial ExamplesMikhail Zolotukhin0https://orcid.org/0000-0001-8058-7902Parsa Miraghaei1Di Zhang2https://orcid.org/0000-0003-2782-3886Timo Hamalainen3https://orcid.org/0000-0002-4168-9102Magister Solutions Ltd, Jyväskylä, FinlandFaculty of Information Technology and Communication Sciences, Tampere University, Tampere, FinlandFaculty of Information Technology, University of Jyväskylä, Jyväskylä, FinlandMagister Solutions Ltd, Jyväskylä, FinlandThe use of artificial intelligence and machine learning is recognized as the key enabler for 5G mobile networks which would allow service providers to tackle the network complexity and ensure security, reliability and allocation of the necessary resources to their customers in a dynamic, robust and trustworthy way. Dependability of the future generation networks on accurate and timely performance of its artificial intelligence components means that disturbance in the functionality of these components may have negative impact on the entire network. As a result, there is an increasing concern about the vulnerability of intelligent machine learning driven frameworks to adversarial effects. In this study, we evaluate various adversarial example generation attacks against multiple artificial intelligence and machine learning models which can potentially be deployed in future 5G networks. First, we describe multiple use cases for which attacks on machine learning components are conceivable including the models employed and the data used for their training. After that, attack algorithms, their implementations and adjustments to the target models are summarised. Finally, the attacks implemented for the aforementioned use cases are evaluated based on deterioration of the objective functions optimised by the target models.https://ieeexplore.ieee.org/document/9968009/5G networksadversarial machine learningartificial intelligencedeep learning |
spellingShingle | Mikhail Zolotukhin Parsa Miraghaei Di Zhang Timo Hamalainen On Assessing Vulnerabilities of the 5G Networks to Adversarial Examples IEEE Access 5G networks adversarial machine learning artificial intelligence deep learning |
title | On Assessing Vulnerabilities of the 5G Networks to Adversarial Examples |
title_full | On Assessing Vulnerabilities of the 5G Networks to Adversarial Examples |
title_fullStr | On Assessing Vulnerabilities of the 5G Networks to Adversarial Examples |
title_full_unstemmed | On Assessing Vulnerabilities of the 5G Networks to Adversarial Examples |
title_short | On Assessing Vulnerabilities of the 5G Networks to Adversarial Examples |
title_sort | on assessing vulnerabilities of the 5g networks to adversarial examples |
topic | 5G networks adversarial machine learning artificial intelligence deep learning |
url | https://ieeexplore.ieee.org/document/9968009/ |
work_keys_str_mv | AT mikhailzolotukhin onassessingvulnerabilitiesofthe5gnetworkstoadversarialexamples AT parsamiraghaei onassessingvulnerabilitiesofthe5gnetworkstoadversarialexamples AT dizhang onassessingvulnerabilitiesofthe5gnetworkstoadversarialexamples AT timohamalainen onassessingvulnerabilitiesofthe5gnetworkstoadversarialexamples |