Differentially Private Federated Learning Based Wideband Spectrum Sensing for the Low-Altitude Unmanned Aerial Vehicle Swarm

DONG Peihao; JIA Jibin; ZHOU Fuhui; WU Qihui

doi:10.11999/JEIT241042

Volume 47 Issue 5

May 2025

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2025 > 47(5): 1345-1355

DONG Peihao, JIA Jibin, ZHOU Fuhui, WU Qihui. Differentially Private Federated Learning Based Wideband Spectrum Sensing for the Low-Altitude Unmanned Aerial Vehicle Swarm[J]. Journal of Electronics & Information Technology, 2025, 47(5): 1345-1355. doi: 10.11999/JEIT241042

Citation:

DONG Peihao, JIA Jibin, ZHOU Fuhui, WU Qihui. Differentially Private Federated Learning Based Wideband Spectrum Sensing for the Low-Altitude Unmanned Aerial Vehicle Swarm[J]. Journal of Electronics & Information Technology, 2025, 47(5): 1345-1355. doi: 10.11999/JEIT241042

Citation:

DONG Peihao, JIA Jibin, ZHOU Fuhui, WU Qihui. Differentially Private Federated Learning Based Wideband Spectrum Sensing for the Low-Altitude Unmanned Aerial Vehicle Swarm[J]. Journal of Electronics & Information Technology, 2025, 47(5): 1345-1355. doi: 10.11999/JEIT241042

PDF( 3030 KB)

Differentially Private Federated Learning Based Wideband Spectrum Sensing for the Low-Altitude Unmanned Aerial Vehicle Swarm

doi: 10.11999/JEIT241042 cstr: 32379.14.JEIT241042

DONG Peihao^{1, 2
,
,},
JIA Jibin¹,
ZHOU Fuhui³,
WU Qihui¹

1.
College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
2.
National Mobile Communications Research Laboratory, Southeast University, Nanjing 211111, China
3.
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China

Funds: The National Natural Science Foundation of China (62471226, 62101253), The Natural Science Foundation of Jiangsu Province (BK20210283), The Open Research Fund of National Mobile Communications Research Laboratory, Southeast University (2022D08), The Fundamental Research Funds for the Central Universities (NS2024023)

Received Date: 2024-11-26
Rev Recd Date: 2025-04-13

Available Online: 2025-04-24

Publish Date: 2025-05-01

Abstract

Abstract

Objective Wideband Spectrum Sensing (WSS) for Unmanned Aerial Vehicles (UAVs) in low-altitude intelligent networks is essential for efficient spectrum monitoring and utilization. However, sampling at the Nyquist rate incurs high hardware and computational costs. Moreover, the high mobility of UAVs subjects them to rapidly changing spectral environments, which significantly reduces sensing accuracy and presents major challenges for UAV-based WSS. Methods A low-complexity Feature-Splitting Wideband Spectrum Sensing neural Network (FS-WSSNet) is proposed to achieve high sensing accuracy while reducing the operational cost of UAVs through sub-Nyquist sampling. To integrate spectral knowledge and computational resources across multiple UAVs and enable adaptation to varying spectrum environments, an online model adaptation algorithm based on Differential Privacy Federated Transfer Learning (DPFTL) is further proposed. Before model parameters are uploaded to a central computation platform, noise is added according to local differential privacy constraints. This enables spectrum knowledge sharing while preserving data privacy within the UAV swarm, allowing FS-WSSNet on each UAV to rapidly adapt to dynamic spectral conditions. Results and Discussions Simulation results demonstrate the effectiveness of the proposed FS-WSSNet and the DPFTL-based online model adaptation algorithm. FS-WSSNet achieves substantially higher prediction accuracy than the comparison models, confirming that omitting convolutional layers degrades performance and supporting the design rationale of FS-WSSNet (Fig. 3). In addition, FS-WSSNet consistently outperforms the baseline scheme across all Signal-to-Noise Ratio (SNR) conditions (Fig. 4). Its Receiver Operating Characteristic (ROC) curve, which lies closer to the top-left corner, indicates improved detection performance across various thresholds (Fig. 5). FS-WSSNet also exhibits significantly lower computational complexity compared with the baseline (Table 1). Furthermore, under the proposed DPFTL-based scheme (Algorithm 1), FS-WSSNet maintains robust performance across different target scenarios without requiring local adaptation samples. This approach not only preserves data privacy but also improves the model’s generalization ability (Figs. 6～9). Conclusions This study proposes a cooperative WSS scheme based on DPFTL for low-altitude UAV swarms. First, data received by UAVs are processed using multicoset sampling to enable cost-efficient sub-Nyquist acquisition. The resulting signals are input into a low-complexity FS-WSSNet for accurate and efficient spectrum detection. An online model adaptation algorithm based on DPFTL is then developed, introducing noise to model parameters before upload to ensure data privacy. By supporting spectrum knowledge sharing and collaborative training, the algorithm effectively integrates the computational and data resources of multiple UAVs to construct a robust model adaptable to various scenarios. Simulation results confirm that the proposed scheme provides an efficient WSS solution for resource-constrained low-altitude UAV networks, achieving both privacy protection and adaptability across scenarios.
- Wideband Spectrum Sensing (WSS),
- Federated Transfer Learning (FTL),
- Differential Privacy (DP),
- Unmanned Aerial Vehicle (UAV)

FullText(HTML)

References(18)

References

[1]	ADIL M, SONG Houbing, MASTORAKIS S, et al. UAV-assisted IoT applications, cybersecurity threats, AI-enabled solutions, open challenges with future research directions[J]. IEEE Transactions on Intelligent Vehicles, 2024, 9(4): 4583–4605. doi: 10.1109/TIV.2023.3309548.
[2]	SHARMA A, VANJANI P, PALIWAL N, et al. Communication and networking technologies for UAVs: A survey[J]. Journal of Network and Computer Applications, 2020, 168: 102739. doi: 10.1016/j.jnca.2020.102739.
[3]	HU Hang, DA Xinyu, HUANG Yangchao, et al. SE and EE optimization for cognitive UAV network based on location information[J]. IEEE Access, 2019, 7: 162115–162126. doi: 10.1109/ACCESS.2019.2951702.
[4]	DONG Peihao, HE Chaowei, GAO Shen, et al. Edge-learning-based collaborative automatic modulation classification for hierarchical cognitive radio networks[J]. IEEE Internet of Things Journal, 2024, 11(21): 34443–34454. doi: 10.1109/JIOT.2024.3431236.
[5]	FANG Jun, WANG Bin, LI Hongbin, et al. Recent advances on sub-Nyquist sampling-based wideband spectrum sensing[J]. IEEE Wireless Communications, 2021, 28(3): 115–121. doi: 10.1109/MWC.001.2000353.
[6]	XU Weibo, WANG Shuo, YAN Shu, et al. An efficient wideband spectrum sensing algorithm for unmanned aerial vehicle communication networks[J]. IEEE Internet of Things Journal, 2019, 6(2): 1768–1780. doi: 10.1109/JIOT.2018.2882532.
[7]	YANG Linxiao, FANG Jun, DUAN Huiping, et al. Fast compressed power spectrum estimation: Toward a practical solution for wideband spectrum sensing[J]. IEEE Transactions on Wireless Communications, 2020, 19(1): 520–532. doi: 10.1109/TWC.2019.2946805.
[8]	WEI Ziping, ZHANG Han, ZHANG Yang, et al. Fast compressed wideband spectrum sensing[J]. IEEE Transactions on Vehicular Technology, 2024, 73(2): 2924–2929. doi: 10.1109/TVT.2023.3318217.
[9]	ZHANG Han, YANG Jian, and GAO Yue. Machine learning empowered spectrum sensing under a sub-sampling framework[J]. IEEE Transactions on Wireless Communications, 2022, 21(10): 8205–8215. doi: 10.1109/TWC.2022.3164800.
[10]	UVAYDOV D, D’ORO S, RESTUCCIA F, et al. DeepSense: Fast wideband spectrum sensing through real-time in-the-loop deep learning[C]. The IEEE INFOCOM 2021 - IEEE Conference on Computer Communications, Vancouver, Canada, 2021: 1–10. doi: 10.1109/INFOCOM42981.2021.9488764.
[11]	MEI Ruru and WANG Zhugang. Deep learning-based wideband spectrum sensing: A low computational complexity approach[J]. IEEE Communications Letters, 2023, 27(10): 2633–2637. doi: 10.1109/LCOMM.2023.3310715.
[12]	MEI Ruru and WANG Zhugang. Compressed spectrum sensing of sparse wideband signals based on deep learning[J]. IEEE Transactions on Vehicular Technology, 2024, 73(6): 8434–8444. doi: 10.1109/TVT.2024.3358026.
[13]	LI Lusi, JIANG He, and HE Haibo. Deep transfer cooperative sensing in cognitive radio[J]. IEEE Wireless Communications Letters, 2021, 10(6): 1354–1358. doi: 10.1109/LWC.2021.3067508.
[14]	SOLANKI S, DEHALWAR V, CHOUDHARY J, et al. Spectrum sensing in cognitive radio using CNN-RNN and transfer learning[J]. IEEE Access, 2022, 10: 113482–113492. doi: 10.1109/ACCESS.2022.3216877.
[15]	DONG Peihao, JIA Jibin, GAO Shen, et al. Pruned convolutional attention network based wideband spectrum sensing with sub-Nyquist sampling[J]. IEEE Transactions on Vehicular Technology, 2025, 74(4): 6817–6822. doi: 10.1109/TVT.2024.3507159.
[16]	WANG Zhibo, SONG Mengkai, ZHANG Zhifei, et al. Beyond inferring class representatives: User-level privacy leakage from federated learning[C]. The IEEE INFOCOM 2019 - IEEE Conference on Computer Communications, Paris, France, 2019: 2512–2520. doi: 10.1109/INFOCOM.2019.8737416.
[17]	DWORK C and ROTH A. The Algorithmic Foundations of Differential Privacy[M]. Boston: Now Publishers Inc. , 2014: 211–407. doi: 10.1561/0400000042.
[18]	MCMAHAN B, MOORE E, RAMAGE D, et al. Communication-efficient learning of deep networks from decentralized data[C]. The 20th International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, USA, 2017: 1273–1282.