A Review on Machine Learning Based Chaos Architectures for Physical Layer Security Through PAPR Reduction

It can observed that wireless networks are bandwidth constrained. Wireless networks suffers from the problem of high PAPR. It is necessary to reduce PAPR and also ensure no or very data loss. High PAPR leads to power inefficiency, signal distortion, and increased vulnerability to eavesdropping because nonlinearities in power amplifiers can unintentionally leak side information. Machine learning-assisted chaos architectures offer several advantages over traditional PAPR reduction and security methods. They simultaneously improve transmission security and amplifier efficiency without requiring excessive computational overhead. Adaptive learning enables real-time optimization under changing channel conditions, while chaotic sequences provide strong resistance against eavesdropping, spoofing, replay attacks, and signal reconstruction. This paper presents a review on the fundamentals of wireless network security along with the problem of PAPR. The various PAPR reduction techniques used in contemporary work have also been cited, for proactive security.

1.                L. Jain and N. Joshi, "Impacts of Web 3.0 on Cyber Security: Challenges and Countermeasures," 2024 International Conference on Artificial Intelligence and Emerging Technology (Global AI Summit), Greater Noida, India, 2024, pp. 912-917. 2.                J Zhu, F Li, J Chen, “A survey of blockchain, artificial intelligence, and edge computing for Web 3.0”, Computer Science Review, Elsevier, 2024, vol.54, 100667. 3.                F. S. Shawqi, L. Audah, A. T. Hammoodi, M. M. Hamdi and A. H. Mohammed, "A Review of PAPR Reduction Techniques for UFMC Waveform," 2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), 2020, pp. 1-6 4.                S. Gökceli et al., "Novel Iterative Clipping and Error Filtering Methods for Efficient PAPR Reduction in 5G and Beyond," in IEEE Open Journal of the Communications Society, 2021, vol. 2, pp. 48-66. 5.                B. Tang, K. Qin and H. Mei, "A Hybrid Approach to Reduce the PAPR of OFDM Signals Using Clipping and Companding," in IEEE Access, 2020, vol. 8, pp. 18984-18994. 6.                R Niwareeba, MA Cox, L Cheng, “Low complexity hybrid SLM for PAPR mitigation for ACO OFDM”, ICT Express, Elsevier 2022, vol.8, no.1, pp.72-76. 7.                W. Ma, C. Qi and G. Y. Li, "High-Resolution Channel Estimation for Frequency-Selective mmWave Massive MIMO Systems," in IEEE Transactions on Wireless Communications, vol. 19, no. 5, pp. 3517-3529, May 2020 8.                K. Venugopal, N. González-Prelcic and R. W. Heath, "Optimality of Frequency Flat Precoding in Frequency Selective Millimeter Wave Channels," in IEEE Wireless Communications Letters, vol. 6, no. 3, pp. 330-333, June 2017. 9.                P. Singh, E. Sharma, K. Vasudevan and R. Budhiraja, "CFO and Channel Estimation for Frequency Selective MIMO-FBMC/OQAM Systems," in IEEE Wireless Communications Letters, vol. 7, no. 5, pp. 844-847, Oct. 2018. 10.             R. Zayani, J. -B. Doré, B. Miscopein and D. Demmer, "Local PAPR-Aware Precoding for Energy-Efficient Cell-Free Massive MIMO-OFDM Systems," in IEEE Transactions on Green Communications and Networking, 2023, vol. 7, no. 3, pp. 1267-1284.