Autoencoder-Based and Subspace Projection Methods for Anomaly Detection in Massive MIMO Systems: A Comparative Analysis

The proposed anomaly detection method for detecting active eavesdropping attacks in wireless systems based on autoencoder and subspace projection technique. The autoencoder learns the normal patterns of the signal and detects anomalies based on the reconstruction error while the subspace method detects anomalies by measuring the change in the energy of the signal in the noise subspace. The results show that both methods work well in different situations. The subspace method is more robust to noise and performs better at low SNR while the autoencoder can capture more complex signal patterns and performs better at moderate and high SNR. Moreover, the performance of detection is better for more antennas and higher transmit power of the eavesdropper. The proposed method shows good potential for improving security in future wireless systems against active attacks.

[1].  P. Chandra Sekhar and T. S. N. Murthy, “RSMO: Rider Spider Monkey Optimization-Based Artificial Noise Precoding Technique for Physical Layer Security in 5G Networks”, Wireless Personal Communications, https://doi.org/10.1007/s11277-024-11166-4. [2].  S. Rajasegarar, C. Leckie, and M. Palaniswami, “Anomaly detection in wireless sensor networks,” IEEE Wireless Communications, vol. 15, no. 4, pp. 34–40, Aug. 2008. [3]. V. Chandola, A. Banerjee, and V. Kumar, “Anomaly detection: A survey,” ACM Computing Surveys, vol. 41, no. 3, pp. 1–58, Jul. 2009. [4]. Y. Zhang, N. Meratnia, and P. Havinga, “Outlier detection techniques for wireless sensor networks: A survey,” IEEE Communications Surveys & Tutorials, vol. 12, no. 2, pp. 159–170, 2010. [5]. Y. Li, M. Chen, and W. Dai, “A lightweight anomaly detection approach for wireless sensor networks,” IEEE Systems Journal, vol. 11, no. 2, pp. 1–10, 2017. [6]. N. Shone, T. N. Ngoc, V. D. Phai, and Q. Shi, “A deep learning approach to network intrusion detection,” IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 2, no. 1, pp. 41–50, Feb. 2018. [7]. T. J. O’Shea and J. Corgan, “Convolutional radio modulation recognition networks,” in Proc. International Conference on Engineering Applications of Neural Networks, 2016. [8].  F. Restuccia, S. D’Oro, and T. Melodia, “Deep learning at the physical layer: System challenges and applications,” IEEE Communications Magazine, vol. 56, no. 10, pp. 78–87, Oct. 2018. [9].  X. Liu, Y. Liu, and A. Liu, “AI-enabled anomaly detection in IoT systems,” IEEE Internet of Things Journal, vol. 7, no. 5, pp. 1–12, 2020. [10]. R. Kumar, P. Singh, and A. K. Verma, “Deep learning-based anomaly detection using CSI in wireless networks,” IEEE Access, vol. 9, pp. 1–12, 2021