Downlink Power Allocation in Massive MIMO via Deep Learning: Adversarial Attacks and Training

被引:8
|
作者
Manoj, B. R. [1 ,2 ]
Sadeghi, Meysam [3 ]
Larsson, Erik G. [4 ]
机构
[1] Linkoping Univ, Dept Elect Engn, Div Commun Syst, S-58183 Linkoping, Sweden
[2] Indian Inst Technol Guwahati, Dept Elect & Elect Engn, Gauhati 781039, India
[3] Linkoping Univ, Div Commun Syst, S-58183 Linkoping, Sweden
[4] Linkoping Univ, Dept Elect Engn ISY, S-58183 Linkoping, Sweden
关键词
Adversarial attacks; adversarial training; black-box attack; deep neural networks; massive MIMO; regression; white-box attack; CLASSIFICATION; NETWORKS;
D O I
10.1109/TCCN.2022.3147203
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
The successful emergence of deep learning (DL) in wireless system applications has raised concerns about new security-related challenges. One such security challenge is adversarial attacks. Although there has been much work demonstrating the susceptibility of DL-based classification tasks to adversarial attacks, regression-based problems in the context of a wireless system have not been studied so far from an attack perspective. The aim of this paper is twofold: (i) we consider a regression problem in a wireless setting and show that adversarial attacks can break the DL-based approach and (ii) we analyze the effectiveness of adversarial training as a defensive technique in adversarial settings and show that the robustness of DL-based wireless system against attacks improves significantly. Specifically, the wireless application considered in this paper is the DL-based power allocation in the downlink of a multicell massive multi-input-multi-output system, where the goal of the attack is to yield an infeasible solution by the DL model. We extend the gradient-based adversarial attacks: fast gradient sign method (FGSM), momentum iterative FGSM, and projected gradient descent method to analyze the susceptibility of the considered wireless application with and without adversarial training. We analyze the deep neural network (DNN) models performance against these attacks, where the adversarial perturbations are crafted using both the white-box and black-box attacks.
引用
收藏
页码:707 / 719
页数:13
相关论文
共 50 条
  • [41] Spectral Efficiency Maximization for Massive Multiuser MIMO Downlink TDD Systems via Data Power Allocation with MRT Precoding
    Saatlou, O.
    Ahmad, M. Omair
    Swamy, M. N. S.
    2017 IEEE 86TH VEHICULAR TECHNOLOGY CONFERENCE (VTC-FALL), 2017,
  • [42] UPLINK POWER CONTROL IN CELL-FREE MASSIVE MIMO VIA DEEP LEARNING
    D'Andrea, Carmen
    Zappone, Alessio
    Buzzi, Stefano
    Debbah, Merouane
    2019 IEEE 8TH INTERNATIONAL WORKSHOP ON COMPUTATIONAL ADVANCES IN MULTI-SENSOR ADAPTIVE PROCESSING (CAMSAP 2019), 2019, : 554 - 558
  • [43] Downlink Training-Based Massive MIMO NOMA
    Kudathanthirige, Dhanushka
    Arnarasuriya, Gayan
    ICC 2020 - 2020 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC), 2020,
  • [44] Beam Allocation based on Deep Learning for Wideband mmWave Massive MIMO
    Zhang, Pengju
    Qi, Chenhao
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, : 913 - 918
  • [45] On the Amount of Downlink Training in Correlated Massive MIMO Channels
    Bazzi, Samer
    Xu, Wen
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2018, 66 (09) : 2286 - 2299
  • [46] Deep Reinforcement Learning-based Power Allocation in Uplink Cell-Free Massive MIMO
    Rahmani, Mostafa
    Bashar, Manijeh
    Dehghani, Mohammad J.
    Xiao, Pei
    Tafazolli, Rahim
    Debbah, Merouane
    2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), 2022, : 459 - 464
  • [47] Deep Learning based Multi-User Power Allocation and Hybrid Precoding in Massive MIMO Systems
    Koc, Asil
    Wang, Mike
    Le-Ngoc, Tho
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, : 5487 - 5492
  • [48] Joint User SCHEDULING and Power Allocation for Massive MIMO Downlink with Two-Stage Precoding
    Sun, Yanhua
    Lv, Susu
    Liu, Shuo
    Zhang, Yan Hua
    2016 2ND IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS (ICCC), 2016, : 2917 - 2921
  • [49] Power Allocation in 1-Bit Massive MIMO Downlink with Zero-Forcing Precoding
    Askerbeyli, Ferhad
    Xu, Wen
    Nossek, Josef A.
    2023 IEEE 34TH ANNUAL INTERNATIONAL SYMPOSIUM ON PERSONAL, INDOOR AND MOBILE RADIO COMMUNICATIONS, PIMRC, 2023,
  • [50] A Low-Complexity Linear Precoding and Power Allocation Scheme for Downlink Massive MIMO Systems
    Zarei, Shahram
    Gerstacker, Wolfgang
    Schober, Robert
    2013 ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS, 2013, : 285 - 290