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
  • [1] Adversarial Attacks on Deep Learning Based Power Allocation in a Massive MIMO Network
    Manoj, B. R.
    Sadeghi, Meysam
    Larsson, Erik G.
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021), 2021,
  • [2] Universal Adversarial Attacks on Neural Networks for Power Allocation in a Massive MIMO System
    Santos, Pablo Millan
    Manoj, B. R.
    Sadeghi, Meysam
    Larsson, Erik G.
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2022, 11 (01) : 67 - 71
  • [3] Defending Adversarial Attacks on Deep Learning-Based Power Allocation in Massive MIMO Using Denoising Autoencoders
    Sahay, Rajeev
    Zhang, Minjun
    Love, David J. J.
    Brinton, Christopher G. G.
    IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2023, 9 (04) : 913 - 926
  • [4] Deep Learning Power Allocation in Massive MIMO
    Sanguinetti, Luca
    Zappone, Alessio
    Debbah, Merouane
    2018 CONFERENCE RECORD OF 52ND ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2018, : 1257 - 1261
  • [5] Deep Learning-based Power Allocation in Massive MIMO Systems with SLNR and SINR Criterions
    Perdana, Ridho Hendra Yoga
    Toan-Van Nguyen
    An, Beongku
    12TH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS (ICUFN 2021), 2021, : 87 - 92
  • [6] Energy Efficiency Optimization Based on Power Allocation in Massive MIMO Downlink Systems
    Liu, Hongmei
    Deng, Honggui
    Yi, Yougen
    Zhu, Zaoxing
    Liu, Gang
    Zhang, Jie
    SYMMETRY-BASEL, 2022, 14 (06):
  • [7] Energy Efficient Power Allocation Algorithm for Downlink Massive MIMO with MRT Precoding
    Zhao, Long
    Zhao, Hui
    Hu, Fanglong
    Zheng, Kan
    Zhang, Jingxing
    2013 IEEE 78TH VEHICULAR TECHNOLOGY CONFERENCE (VTC FALL), 2013,
  • [8] Massive MU-MIMO Downlink Training with Orthogonal Pilots Allocation
    Qian, Cheng
    Yang, Haifen
    Li, Guangjun
    2018 41ST INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING (TSP), 2018, : 559 - 564
  • [9] Adversarial attacks and adversarial training for burn image segmentation based on deep learning
    Chen, Luying
    Liang, Jiakai
    Wang, Chao
    Yue, Keqiang
    Li, Wenjun
    Fu, Zhihui
    MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2024, 62 (09) : 2717 - 2735
  • [10] Learning-Based Downlink Power Allocation in Cell-Free Massive MIMO Systems
    Zaher, Mahmoud
    Demir, Ozlem Tugfe
    Bjornson, Emil
    Petrova, Marina
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2023, 22 (01) : 174 - 188