Adversarial defense method based on ensemble learning for modulation signal intelligent recognition

被引:2
作者
Han, Chao [1 ]
Qin, Ruoxi [1 ]
Wang, Linyuan [1 ]
Cui, Weijia [1 ]
Chen, Jian [1 ]
Yan, Bin [1 ]
机构
[1] Peoples Liberat Army Strateg Support Force Informa, Zhengzhou, Peoples R China
关键词
Intelligent recognition model; Adversarial defense; Ensemble learning; CW Attack;
D O I
10.1007/s11276-023-03299-4
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Modulation signal intelligent recognition model based on deep learning is widely used in the field of radio signal intelligent processing, but the adversarial attack has become a huge security threat. In order to promote the safe and reliable application of the modulation recognition intelligent model, it is necessary to study its adversarial defense technology. An adversarial defense method based on ensemble learning for modulation signal intelligent recognition model is proposed in this paper. Specifically, this method is achieved by combining multiple defense models such as adversarial training, defensive distillation, and noise smoothing. Variety of attack algorithms in both the white-box and black-box scenarios under different intensities of perturbation and different signal-to-noise ratios are carried out to verify the robustness performance of the proposed method. Strikingly, the accuracy of the model is improved to over 80% when the SNR is above 0 dB under Carlini and Wagner attack.
引用
收藏
页码:2967 / 2980
页数:14
相关论文
共 43 条
[1]  
Adesina D., 2022, IEEE Communications Surveys & Tutorials
[2]  
[Anonymous], 2016, P GNU RADIO C
[3]   Threat of Adversarial Attacks on DL-Based IoT Device Identification [J].
Bao, Zhida ;
Lin, Yun ;
Zhang, Sicheng ;
Li, Zixin ;
Mao, Shiwen .
IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (11) :9012-9024
[4]   Towards Evaluating the Robustness of Neural Networks [J].
Carlini, Nicholas ;
Wagner, David .
2017 IEEE SYMPOSIUM ON SECURITY AND PRIVACY (SP), 2017, :39-57
[5]   Defensive Distillation-Based Adversarial Attack Mitigation Method for Channel Estimation Using Deep Learning Models in Next-Generation Wireless Networks [J].
Catak, Ferhat Ozgur ;
Kuzlu, Murat ;
Catak, Evren ;
Cali, Umit ;
Guler, Ozgur .
IEEE ACCESS, 2022, 10 :98191-98203
[6]  
Cohen Jeremy, 2019, Certified Adversarial Robustness via Randomized Smoothing, P1310
[7]   Boosting Adversarial Attacks with Momentum [J].
Dong, Yinpeng ;
Liao, Fangzhou ;
Pang, Tianyu ;
Su, Hang ;
Zhu, Jun ;
Hu, Xiaolin ;
Li, Jianguo .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :9185-9193
[8]   Wideband Spectral Monitoring Using Deep Learning [J].
Franco, Horacio ;
Cobo-Kroenke, Chris ;
Welch, Stephanie ;
Graciarena, Martin .
PROCEEDINGS OF THE 2ND ACM WORKSHOP ON WIRELESS SECURITY AND MACHINE LEARNING, WISEML 2020, 2020, :19-24
[9]  
Fu X., 2023, IEEE Internet Things J
[10]   Automatic Modulation Classification Based on Decentralized Learning and Ensemble Learning [J].
Fu, Xue ;
Gui, Guan ;
Wang, Yu ;
Gacanin, Haris ;
Adachi, Fumiyuki .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2022, 71 (07) :7942-7946