ABSTRACT
Wireless spectrum anomaly detection aims to identify anomaly signals in the environment and spectrum usage behavior, holding significant implications for spectrum regulation. Due to the complexity of frequency bands composition and the diversity of anomalies, spectrum anomaly detection faces numerous challenges. This paper proposes an improved wireless spectrum anomaly detection model with adaptive attention mechanism, intending to cope the impact of unsupervised anomaly detection on noise floor in spectrum and enhance anomaly detection accuracy. The proposed adaptive attention mechanism adjusts the model's attention to different parts of the spectrum, alleviates the attention to noise floor in spectrum, and optimizes the model feature extraction process. A novel anomaly scoring is introduced to provide a more accurate metric for anomaly detection in different scenarios, particularly in low interference-to-signal ratio environments, significantly improving the model's detection accuracy. Experimental validation on collected spectrum data demonstrates that the proposed model outperforms existing models in terms of performance.
- Ding G, Jiao Y, Wang J, Spectrum inference in cognitive radio networks: Algorithms and applications[J]. IEEE Communications Surveys & Tutorials, 2017, 20(1): 150-182.Google ScholarCross Ref
- Mu X M, Shi G Q, Liu Y A contract based on the cognitive network collaborative spectrum sharing strategy [J]. Journal of zhengzhou university (engineering science), 2016, 5 (3) : 1-5. DOI: 10.13705 / j.i SSN. 1671-6833.2016.03.001.Google Scholar
- Rajendran S, Pollin S. Large‐scale Wireless Spectrum Monitoring: Challenges and Solutions based on Machine Learning[J]. Spectrum Sharing: The Next Frontier in Wireless Networks, 2020: 321-339.Google Scholar
- Kingma D P, Welling M. Auto-encoding variational bayes[J]. arXiv preprint arXiv:1312.6114, 2013.Google Scholar
- Sarala B, Devi S R, Sheela J J J. Spectrum energy detection in cognitive radio networks based on a novel adaptive threshold energy detection method[J]. Computer Communications, 2020, 152: 1-7.Google ScholarCross Ref
- Shbat M, Tuzlukov V. Primary signal detection algorithms for spectrum sensing at low SNR over fading channels in cognitive radio[J]. Digital Signal Processing, 2019, 93: 187-207.Google ScholarDigital Library
- Dong Q, Yang Z, Chen Y, Exploration of singular spectrum analysis for online anomaly detection in crns[J]. EAI Endorsed Transactions on Security and Safety, 2017, 4(12).Google Scholar
- Shao G, Chen Y, Wei Y. Deep fusion for radar jamming signal classification based on CNN[J]. IEEE Access, 2020, 8: 117236-117244.Google ScholarCross Ref
- Hou Y, Ren H, Lv Q, Radar-Jamming Classification in the Event of Insufficient Samples Using Transfer Learning[J]. Symmetry, 2022, 14(11): 2318.Google ScholarCross Ref
- O'Shea T J, Clancy T C, McGwier R W. Recurrent neural radio anomaly detection[J]. arXiv preprint arXiv:1611.00301, 2016.Google Scholar
- Feng Q, Zhang Y, Li C, Anomaly detection of spectrum in wireless communication via deep auto-encoders[J]. The Journal of Supercomputing, 2017, 73: 3161-3178.Google ScholarDigital Library
- Rajendran S, Meert W, Lenders V, Unsupervised wireless spectrum anomaly detection with interpretable features[J]. ieee transactions on cognitive communications and networking, 2019, 5(3): 637-647.Google Scholar
- Zhou X, Xiong J, Zhang X, A radio anomaly detection algorithm based on modified generative adversarial network[J]. IEEE Wireless Communications Letters, 2021, 10(7): 1552-1556.Google ScholarCross Ref
- Tschimben S. Anomaly Detection in Shared Spectrum[D]. University of Colorado at Boulder, 2022.Google ScholarDigital Library
- Horn R A. The hadamard product[C]//Proc. Symp. Appl. Math. 1990, 40: 87-169.Google Scholar
- Tian Y, Liao H, Xu J, Unsupervised spectrum anomaly detection method for unauthorized bands[J]. Space: Science & Technology, 2022.Google ScholarCross Ref
- Zhang F, Shi X F, ZHANG X Z. Simulation and Analysis of Welch power Spectrum Estimation Algorithm [J]. Journal of Xi 'an Technological University,2009,29(04):353-356.Google Scholar
- He K, Zhang X, Ren S, Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.Google Scholar
Index Terms
- An Improved Wireless Spectrum Anomaly Detection Model with Adaptive Attention Mechanism
Recommendations
Anomaly detection of spectrum in wireless communication via deep auto-encoders
Anomaly detection is a typical task in many fields, as well as spectrum monitoring in wireless communication. Anomaly detection task of spectrum in wireless communication is quite different from other anomaly detection tasks, mainly reflected in two ...
An Anomaly Detection and Localization Method Based on Feature Fusion and Attention
Artificial Intelligence Security and PrivacyAbstractIn the context of anomaly detection and localization, the small proportion of anomaly data and its unknown nature increase the difficulty of the model in learning the anomaly information. At the same time, the current mainstream detection methods ...
Temporal-spectral data mining in anomaly detection for spectrum monitoring
WiCOM'09: Proceedings of the 5th International Conference on Wireless communications, networking and mobile computingAs the wireless services developed rapidly in the recent years, a diversity of wireless services emerge such that radio environment becomes more and more complicated. Radio Spectrum security is now attached with great importance. Real time spectrum ...
Comments