Mixed secure autoprecoder design for MIMO broadcast channel with confidential messages

Abstract

Deep learning (DL) exhibits great potential in addressing the nonconvex optimization challenges for secure precoding in multiple-input multiple-output (MIMO) communication systems. However, existing studies rarely consider the internal eavesdropping threat where legitimate users may intercept confidential messages intended for other users. To fill this gap, a mixed secure autoprecoder (MSAP) approach is proposed for two-user MIMO broadcast channels with confidential messages. The MSAP jointly designs a data-driven autoencoder (AE) and a model-driven zero-forcing (ZF) constraint to optimize the transmitter and receivers simultaneously, ensuring that each user’s signal is nulled at the unintended receiver to guarantee confidentiality. Extensive simulation results demonstrate that the MSAP achieves stronger security against legitimate eavesdroppers and lower symbol error rate (SER) for reliable transmission, and outperforms existing schemes.

Keywords

multiple-input multiple-output (MIMO) broadcast channel / physical layer security / autoencoder (AE) / zero-forcing (ZF) / confidential messages

References

[1] ZHANG Z Q, XIAO Y, MA Z, et al. 6G wireless networks: vision, requirements, architecture, and key technologies. IEEE Vehicular Technology Magazine, 2019, 14(3): 28-41.

[2] YU W, SOHRABI F, JIANG T . Role of deep learning in wireless communications. IEEE Information Theory Magazine, 2022, 2(2): 56-72.

[3] PAULS J, VAEZI M . Secure precoding in MIMO-NOMA: a deep learning approach. IEEE Wireless Communications Letters, 2022, 11(1): 77-80.

[4] ZHANG S, LIU Y S, GAO F F, et al. Deep learning based channel extrapolation for large-scale antenna systems: opportunities, challenges and solutions. IEEE Wireless Communications, 2021, 28(6): 160-167.

[5] O'SHEA T, HOYDIS J. An introduction to deep learning for the physical layer. IEEE Transactions on Cognitive Communications and Networking, 2017, 3(4): 563-575.

[6] O'SHEA T J, ERPEK T, CLANCY T C . Deep learning-based MIMO communications. arXiv Preprint, arXiv:1707.07980, 2017.

[7] ZHANG X l, VAEZI M, O'SHEA T J . SVD-embedded deep autoencoder for MIMO communications. Proceedings of the 2022 IEEE International Conference on Communications (ICC'22), 2022, May 16 - 20, Seoul, Republic of Korea. Piscataway, NJ, USA: IEEE, 2022: 5190-5195.

[8] SONG J X, HÄGER C, SCHRÖDER J, et al. Benchmarking and interpreting end-to-end learning of MIMO and multi-user communication. IEEE Transactions on Wireless Communications, 2022, 21(9): 7287-7298.

[9] QI Y, VAEZI M . Secure transmission in MIMO-NOMA networks. IEEE Communications Letters, 2020, 24(12): 2696-2700.

[10] LI B, FEI Z S, ZHOU C Q, et al. Physical-layer security in space information networks: a survey. IEEE Internet of Things Journal, 2020, 7(1): 33-52.

[11] FRITSCHEK R, SCHAEFER R F, WUNDER G. Deep learning for the Gaussian wiretap channel. Proceedings of the 2019 IEEE International Conference on Communications (ICC'19), 2019, May 20 - 24, Shanghai, China. Piscataway, NJ, USA: IEEE, 2019: 6p.

[12] WANG X Y, ZHENG Z, FEI Z S . ASAP: adversarial learning based secure autoprecoder design for MIMO wiretap channels. IEEE Wireless Communications Letters, 2022, 11(9): 1915-1919.

[13] GOLDFELD Z, PERMUTER H H . MIMO Gaussian broadcast channels with common, private, and confidential messages. IEEE Transactions on Informationn Theory, 2019, 65(4): 2525-2544.

[14] WANG Q, ZHANG T J, DONG D L, et al. Secure degrees of freedom of rank-deficient BCCM and rank-deficient ICCM. IEEE Transactions on Vehicular Technology, 2020, 69(4): 4033-4041.

[15] SOHRABI F, YU W . Hybrid digital and analog beamforming design for large-scale antenna arrays. IEEE Journal of Selected Topics in Signal Processing, 2016, 10(3): 501-513.

[16] TRAN L N, JUNTTI M, BENGTSSON M, et al. Successive zero-forcing DPC with sum power constraint: low-complexity optimal designs. Proceedings of the 2012 IEEE International Conference on Communications (ICC'12), 2012, Jun 10 - 15, Ottawa, Canada. Piscataway, NJ, USA: IEEE, 2012: 4857-4861.