Security of AI-Driven Beam Selection for Distributed MIMO in an Adversarial Setting
In distributed multiple-input multiple-output (D-MIMO) networks, beam selection is necessary to predict the best beam and radio units (RUs) to serve the users in an optimum way. Finding the best RU and beam requires measuring the downlink channel for all possible RU/beam pairs, which becomes a resou...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10474020/ |
| _version_ | 1797243445428879360 |
|---|---|
| author | Omer Faruk Tuna Fehmi Emre Kadan |
| author_facet | Omer Faruk Tuna Fehmi Emre Kadan |
| author_sort | Omer Faruk Tuna |
| collection | DOAJ |
| description | In distributed multiple-input multiple-output (D-MIMO) networks, beam selection is necessary to predict the best beam and radio units (RUs) to serve the users in an optimum way. Finding the best RU and beam requires measuring the downlink channel for all possible RU/beam pairs, which becomes a resource-heavy operation, especially at the millimeter Wave band. To overcome this problem, artificial intelligence (AI) solutions are investigated which aim to infer the best RU/beam from sounding the channel for a subset of RUs and beams. While fairly accurate AI models can be obtained, these models have some intrinsic vulnerabilities to adversarial attacks where carefully designed perturbations are applied to the input of the AI model. In this study, we consider four different adversarial attack methods that craft perturbations using gradients of the AI cost function under two different beam reporting scenarios considering sequential and one-shot reporting of reference signal received power values for all RUs and demonstrate their effectiveness over traditional methods by extensive simulations, showing the necessity of smart defense techniques. To this aim, we propose an effective mitigation solution based on scrambling of RUs against these kinds of adversarial attack threats and verify the efficacy of our solution via detailed simulations. The proposed defense method provides up to 10 dB better signal strengths at the user side by selecting more accurate RU/beam pairs under adversarial attacks. |
| first_indexed | 2024-04-24T18:55:14Z |
| format | Article |
| id | doaj.art-70a766dcbd424007835e94793f03efb5 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T18:55:14Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-70a766dcbd424007835e94793f03efb52024-03-26T17:43:53ZengIEEEIEEE Access2169-35362024-01-0112420284204110.1109/ACCESS.2024.337826310474020Security of AI-Driven Beam Selection for Distributed MIMO in an Adversarial SettingOmer Faruk Tuna0https://orcid.org/0000-0002-6214-6262Fehmi Emre Kadan1Ericsson Research, Ericsson Turkey, Istanbul, TurkeyEricsson Research, Ericsson Turkey, Istanbul, TurkeyIn distributed multiple-input multiple-output (D-MIMO) networks, beam selection is necessary to predict the best beam and radio units (RUs) to serve the users in an optimum way. Finding the best RU and beam requires measuring the downlink channel for all possible RU/beam pairs, which becomes a resource-heavy operation, especially at the millimeter Wave band. To overcome this problem, artificial intelligence (AI) solutions are investigated which aim to infer the best RU/beam from sounding the channel for a subset of RUs and beams. While fairly accurate AI models can be obtained, these models have some intrinsic vulnerabilities to adversarial attacks where carefully designed perturbations are applied to the input of the AI model. In this study, we consider four different adversarial attack methods that craft perturbations using gradients of the AI cost function under two different beam reporting scenarios considering sequential and one-shot reporting of reference signal received power values for all RUs and demonstrate their effectiveness over traditional methods by extensive simulations, showing the necessity of smart defense techniques. To this aim, we propose an effective mitigation solution based on scrambling of RUs against these kinds of adversarial attack threats and verify the efficacy of our solution via detailed simulations. The proposed defense method provides up to 10 dB better signal strengths at the user side by selecting more accurate RU/beam pairs under adversarial attacks.https://ieeexplore.ieee.org/document/10474020/Adversarial machine learningbeam selectioncell-free massive MIMOdeep learningdistributed MIMOsecurity |
| spellingShingle | Omer Faruk Tuna Fehmi Emre Kadan Security of AI-Driven Beam Selection for Distributed MIMO in an Adversarial Setting IEEE Access Adversarial machine learning beam selection cell-free massive MIMO deep learning distributed MIMO security |
| title | Security of AI-Driven Beam Selection for Distributed MIMO in an Adversarial Setting |
| title_full | Security of AI-Driven Beam Selection for Distributed MIMO in an Adversarial Setting |
| title_fullStr | Security of AI-Driven Beam Selection for Distributed MIMO in an Adversarial Setting |
| title_full_unstemmed | Security of AI-Driven Beam Selection for Distributed MIMO in an Adversarial Setting |
| title_short | Security of AI-Driven Beam Selection for Distributed MIMO in an Adversarial Setting |
| title_sort | security of ai driven beam selection for distributed mimo in an adversarial setting |
| topic | Adversarial machine learning beam selection cell-free massive MIMO deep learning distributed MIMO security |
| url | https://ieeexplore.ieee.org/document/10474020/ |
| work_keys_str_mv | AT omerfaruktuna securityofaidrivenbeamselectionfordistributedmimoinanadversarialsetting AT fehmiemrekadan securityofaidrivenbeamselectionfordistributedmimoinanadversarialsetting |