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
  • [21] A Deep Learning Model for Optimizing Downlink Parameters of Wireless Information and Power Transfer in Massive MIMO Networks
    Elrashidy, Mohamed
    Masood, Mudassir
    Nasir, Ali Arshad
    INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS, 2025, 38 (05)
  • [22] Outage-Constrained Transceiver Power Loading: A Deep Learning Approach to Robust Massive MIMO Downlink
    Li, Yundi
    Lu, Guanxing
    Zhou, Huapeng
    Wang, Yafei
    Wang, Wenjin
    2022 IEEE INTERNATIONAL BLACK SEA CONFERENCE ON COMMUNICATIONS AND NETWORKING (BLACKSEACOM), 2022, : 197 - 201
  • [23] Max-Min Multicell-Aware Precoding and Power Allocation for Downlink Massive MIMO Systems
    Zarei, Shahram
    Aulin, Jocelyn
    Gerstacker, Wolfgang
    Schober, Robert
    IEEE SIGNAL PROCESSING LETTERS, 2017, 24 (10) : 1433 - 1437
  • [24] Joint Resource Allocation for Linear Precoding in Downlink Massive MIMO Systems
    Zhang, Yuhao
    Mitran, Patrick
    Rosenberg, Catherine
    IEEE TRANSACTIONS ON COMMUNICATIONS, 2021, 69 (05) : 3039 - 3053
  • [25] Interleaved Training for Massive MIMO Downlink via Exploring Channel Temporal Correlation
    Zhang, Cheng
    Liu, Chang
    Jing, Yindi
    Fan, Yiwu
    Huang, Yongming
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2024, 13 (12) : 3444 - 3448
  • [26] Dynamic Power Allocation for Cell-Free Massive MIMO: Deep Reinforcement Learning Methods
    Zhao, Yu
    Niemegeers, Ignas G.
    De Groot, Sonia M. Heemstra
    IEEE ACCESS, 2021, 9 (09) : 102953 - 102965
  • [27] Joint Optimal Number of RF chains and Power Allocation for Downlink Massive MIMO Systems
    Hamdi, Rami
    Ajib, Wessam
    2015 IEEE 82ND VEHICULAR TECHNOLOGY CONFERENCE (VTC FALL), 2015,
  • [28] Deep Learning for Detection and Identification of Asynchronous Pilot Spoofing Attacks in Massive MIMO Networks
    Choudhury, Fuad
    Ikhlef, Aissa
    Saad, Walid
    Debbah, Merouane
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2024, 23 (11) : 17103 - 17114
  • [29] Modified fractional power allocation for downlink cell-free massive MIMO systems
    Zhang, Xiaohui
    Wang, Dongle
    Xing, Ling
    Wu, Honghai
    PHYSICAL COMMUNICATION, 2024, 67
  • [30] Adversarial Attacks on Deep Learning Models of Computer Vision: A Survey
    Ding, Jia
    Xu, Zhiwu
    ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2020, PT III, 2020, 12454 : 396 - 408