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] Deep learning based user scheduling for massive MIMO downlink system
    Xiaoxiang Yu
    Jiajia Guo
    Xiao Li
    Shi Jin
    Science China Information Sciences, 2021, 64
  • [22] Deep learning based user scheduling for massive MIMO downlink system
    Xiaoxiang YU
    Jiajia GUO
    Xiao LI
    Shi JIN
    Science China(Information Sciences), 2021, 64 (08) : 66 - 75
  • [23] Deep learning based user scheduling for massive MIMO downlink system
    Yu, Xiaoxiang
    Guo, Jiajia
    Li, Xiao
    Jin, Shi
    SCIENCE CHINA-INFORMATION SCIENCES, 2021, 64 (08)
  • [24] Deep Learning Based Robust Precoder Design for Massive MIMO Downlink
    Shi, Junchao
    Wang, Wenjin
    Yi, Xinping
    Gao, Xiqi
    Li, Geoffrey Ye
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021), 2021,
  • [25] 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)
  • [26] 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
  • [27] 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
  • [28] Downlink training scheme for massive MIMO systems
    Qian, Chen
    Wang, Zhaocheng
    Dai, Linglong
    Chen, Jinhui
    Sun, Chen
    ELECTRONICS LETTERS, 2015, 51 (24) : 2059 - 2060
  • [29] 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
  • [30] Effect of Limited Number of RF Chains and Training Power on Massive MIMO Downlink
    Khichar, Sunita
    Santipach, Wiroonsak
    Wuttisittikulkij, Lunchakorn
    2024 21ST INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING/ELECTRONICS, COMPUTER, TELECOMMUNICATIONS AND INFORMATION TECHNOLOGY, ECTI-CON 2024, 2024,