AIR: Threats of Adversarial Attacks on Deep Learning-Based Information Recovery

被引:2
作者
Chen, Jinyin [1 ]
Ge, Jie [2 ]
Zheng, Shilian [3 ]
Ye, Linhui [4 ]
Zheng, Haibin [1 ]
Shen, Weiguo [3 ]
Yue, Keqiang [5 ]
Yang, Xiaoniu [3 ]
机构
[1] Zhejiang Univ Technol, Inst Cyberspace Secur, Hangzhou 310023, Peoples R China
[2] Zhejiang Univ Technol, Coll Informat Engn, Hangzhou 310023, Peoples R China
[3] Natl Key Lab Electromagnet Space Secur, Innovat Studio Academician Yang, Jiaxing 314000, Peoples R China
[4] Zhejiang Univ, Binjiang Inst, Hangzhou 310023, Peoples R China
[5] Hangzhou Dianzi Univ, Key Lab RF Circuits & Syst, Minist Educ, Hangzhou, Zhejiang, Peoples R China
基金
中国国家自然科学基金;
关键词
Receivers; Perturbation methods; Modulation; Atmospheric modeling; Peak to average power ratio; Wireless communication; Sensors; Wireless communication system; information recovery; receiver; deep learning; adversarial attack; CHANNEL ESTIMATION; RECEIVER; DEFENSE;
D O I
10.1109/TWC.2024.3374699
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
A wireless communications system usually consists of a transmitter which transmits the information and a receiver which recovers the original information from the received distorted signal. Deep learning (DL) has been used to improve the performance of the receiver in complicated channel environments and state-of-the-art (SOTA) performance has been achieved. However, its robustness has not been investigated. In order to evaluate the robustness of DL-based information recovery models under adversarial circumstances, we investigate adversarial attacks on the SOTA DL-based information recovery model, i.e., DeepReceiver. We formulate the problem as an optimization problem with power and peak-to-average power ratio (PAPR) constraints. We design different adversarial attack methods according to the adversary's knowledge of DeepReceiver's model and/or testing samples. Extensive experiments show that the DeepReceiver is vulnerable to the designed attack methods in all of the considered scenarios. Even in the scenario of both model and test sample restricted, the adversary can attack the DeepReceiver and increase its bit error rate (BER) above 10%. It can also be found that the DeepReceiver is vulnerable to adversarial perturbations even with very low power and limited PAPR. These results suggest that defense measures should be taken to enhance the robustness of DeepReceiver.
引用
收藏
页码:10698 / 10711
页数:14
相关论文
共 56 条
  • [1] Adil M., IEEE Trans. Intell. Vehicles, early access, DOI [10.1109/TTV.2023.3309548, DOI 10.1109/TTV.2023.3309548]
  • [2] Asgharzadeh M, 2013, Arxiv, DOI arXiv:1312.6799
  • [3] Deep Learning-Based Channel Estimation Algorithm Over Time Selective Fading Channels
    Bai, Qinbo
    Wang, Jintao
    Zhang, Yue
    Song, Jian
    [J]. IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2020, 6 (01) : 125 - 134
  • [4] Milestones in Autonomous Driving and Intelligent Vehicles-Part 1: Control, Computing System Design, Communication, HD Map, Testing, and Human Behaviors
    Chen, Long
    Li, Yuchen
    Huang, Chao
    Xing, Yang
    Tian, Daxin
    Li, Li
    Hu, Zhongxu
    Teng, Siyu
    Lv, Chen
    Wang, Jinjun
    Cao, Dongpu
    Zheng, Nanning
    Wang, Fei-Yue
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2023, 53 (09): : 5831 - 5847
  • [5] A CLUSTERING TECHNIQUE FOR DIGITAL-COMMUNICATIONS CHANNEL EQUALIZATION USING RADIAL BASIS FUNCTION NETWORKS
    CHEN, S
    MULGREW, B
    GRANT, PM
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (04): : 570 - 579
  • [6] A Mobile Phone Uplink CPDP-DTDOA Positioning Method Using UAVs for Search and Rescue
    Deng, Zhongliang
    Gao, Yuhui
    Hu, Aihua
    Zhang, Yao
    [J]. IEEE SENSORS JOURNAL, 2022, 22 (18) : 18170 - 18179
  • [7] Doan N, 2019, IEEE ICC
  • [8] Boosting Adversarial Attacks with Momentum
    Dong, Yinpeng
    Liao, Fangzhou
    Pang, Tianyu
    Su, Hang
    Zhu, Jun
    Hu, Xiaolin
    Li, Jianguo
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 9185 - 9193
  • [9] Fang LT, 2017, 2017 IEEE 2ND INTERNATIONAL CONFERENCE ON OPTO-ELECTRONIC INFORMATION PROCESSING (ICOIP), P16, DOI 10.1109/OPTIP.2017.8030690
  • [10] Evaluating Adversarial Evasion Attacks in the Context of Wireless Communications
    Flowers, Bryse
    Buehrer, R. Michael
    Headley, William C.
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2020, 15 (15) : 1102 - 1113