Chaotic deep neural network based physical layer key generation for massive MIMO

Siyad, C. Ismayil; Tamilselvan, S.

doi:10.1007/s41870-021-00751-6

Cited by 4 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This reveals that constrained eavesdropping can significantly increase the possible SKR, providing higher precision and lower SKR. Using Chua's chaotic dynamics for DL-dependent physical layer encryption key generation, Ismayil Siyad, C. and Tamilselvan, S., 2021, [23] presented a chaotic DNN-dependent PLKG for massive MIMO. The system offers a higher SKR and lower transmission distance.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Real testing with standard telecom fibres, which already prevail, is crucial; these implementations often rely on outdated theories that overlook various sources of errors, emphasizing the imperative need for more comprehensive analyses and optimizations in quantum communication setups. Addressing these challenges is essential for evaluating device imperfections and characterizing bit errors caused by source line width, electro-optical modulation, chromatic dispersion, and detector dark counts to enhance performance for higher SKRs and lower QBERs in a phase-dependent QKD system [21][22][23][24][25][26][27]. To analyse device flaws and characterize bit errors caused by chromatic dispersion, detector dark counts, source line width, electro-optical modulation, and other factors to maximize performance for low QBERs and higher SKRs in phase-dependent QKD systems.…”

Section: Problem Statement and Motivation Behind This Researchmentioning

confidence: 99%

See 1 more Smart Citation

Enhanced Quantum Key Distribution and Error Minimization for 6G Networks through Optimized Multi-Head Self-Attention and Gated-Dilated Convolutional Neural Networks

Dhandapani,

Jothi

2024

Preprint

View full text Add to dashboard Cite

6G frameworks will be able to utilize higher frequencies than 5G frameworks and provide altogether higher capacity and much lower latency. First, 6G network input signals stand up to channel obstacles to open security. QKD, a cryptographic technique, allows two parties to safely exchange secret keys for message encryption and decryption. Based on quantum mechanics, any threats in the system warn the authorized users. Qubits can be distributed over fibre or free space quantum channels and encoded with several degrees of freedom. In this proposed method, QKD and Error Rate Optimization using an optimized Multi-Head Self-Attention and Gated-Dilated Convolutional Neural Network (QKD-ERO-MSGCNN) are used to extend the maximum transmission distance and improve the secret key rate (SKR). The variable velocity strategy particle swarm optimization algorithm (VVSPSOA) is used on the input signals to improve the SKR and is fed to the MSGCNN to analyse the quantum bit error rate (QBER) reduction effectively. MSGCNN alone does not optimize the QBER reduction in the channel accurately; intensified sand cat swarm optimization (ISCSO) is used to analyse the QBER reduction accurately. The proposed QKD-ERO-MSGCNN is implemented, and metrics such as accuracy, precision, SKR and QBER reduction attain higher performances when compared with existing techniques.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Problem Statement and Motivation Behind This Researchmentioning

confidence: 99%

Enhanced Quantum Key Distribution and Error Minimization for 6G Networks through Optimized Multi-Head Self-Attention and Gated-Dilated Convolutional Neural Networks

Dhandapani,

Jothi

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Nonetheless, all of the proposed strategies are precisely based on the non-M-MIMO systems and considered ideal transceiver hardware design which is not a practical approach. Though few recent studies have utilized intelligent learning techniques [113,114], particularly for upcoming aerial platform scenarios [27,115], more advanced approaches are much needed.…”

Section: Securitymentioning

confidence: 99%

Multi-antenna Arrays Based Massive-MIMO for B5G/6G: State-of-the-Art, Challenges and Future Research Directions

Qamar,

Kazmi,

Ariffin

et al. 2024

Preprint

View full text Add to dashboard Cite

This comprehensive article explores Massive MIMO (M-MIMO) design and its associated concepts, focusing on the seamless integration requirements for Beyond 5G (B5G) and 6G networks. Addressing critical aspects such as RF chain reduction, pilot contamination, Cell-Free MIMO, and security considerations, the article delves into the intricacies of M-MIMO in the evolving landscape of B5G. Moreover, the emerging MIMO concepts in this article include AI-enabled M-MIMO three-dimensional beamforming, reconfigurable intelligent surfaces, visible light communication, and THz spectrum utilization. This review highlights challenges and open research issues, including Narrow Aperture Antenna Nodes, Plasmonic Antenna Arrays, Integrated Sensing with M-MIMO, and the application of Federated Learning in M-MIMO systems. By examining these cutting-edge developments, the article aims to contribute to advancing knowledge in the field and inspire future research directions in the exciting realm of B5G and 6G networks.

show abstract

Chaotic driven gorilla troops optimizer based NMF approach for integrative analysis of multiple source data

Bansal

Sahoo

2022

Int. j. inf. tecnol.

View full text Add to dashboard Cite

Chaotic deep neural network based physical layer key generation for massive MIMO

Cited by 4 publications

References 44 publications

Enhanced Quantum Key Distribution and Error Minimization for 6G Networks through Optimized Multi-Head Self-Attention and Gated-Dilated Convolutional Neural Networks

Enhanced Quantum Key Distribution and Error Minimization for 6G Networks through Optimized Multi-Head Self-Attention and Gated-Dilated Convolutional Neural Networks

Multi-antenna Arrays Based Massive-MIMO for B5G/6G: State-of-the-Art, Challenges and Future Research Directions

Chaotic driven gorilla troops optimizer based NMF approach for integrative analysis of multiple source data

Contact Info

Product

Resources

About