Nature-Inspired Gravitational Search-Guided Artificial Neural Key Exchange for IoT Security Enhancement

The advantages of IoT are incontrovertible; however, significant risks and uncertainties over the protection of best practices and their related costs prevent many companies from adopting the technology. Also, users are aware of the consequences of breaches of IoT protection. Recent research indicates that 90% of consumers lack confidence in the safety of IoT devices. IoT defense has been described as one of the weakest areas. In this respect, significant efforts have been made, often through traditional cryptographic methods, to overcome security and privacy issues in IoT systems. The list of security issues (confidentiality, integrity, authentication, and availability) must be addressed to secure IoT devices from attack. IoT nodes’ specific features do not adequately protect the whole security spectrum of IoT networks through existing solutions. This paper aims to provide security to the IoT devices using nature-inspired Gravitational Search-guided artificial neural key. In this paper, artificial neural synchronization is used to create a neural key exchange protocol between two IoT devices over a public channel for cryptographic purposes. This proposed technique has many benefits, such as 1) it provides an optimized design of the neural network that facilitates the development and establishment of a neural key between the two approved IoT devices. 2) It offers the sharing of the private neural key over the public channel via artificial neural synchronization 3)Three hidden layers of the neural network contribute to the deep internal design. So, it’s going to be hard for the intruder to infer the internal layout. 4) The increase in the weight spectrum of the neural network raises the complexity of an effective attack exponentially, but the effort to create a neural key decreases over polynomial time. Various parametric experiments have been conducted out on the proposed methodology. The simulations of the procedure demonstrate efficacy in terms of the findings cited in the paper.

[1]  Pranita P. Hadke,et al.  Use of Neural Networks in cryptography: A review , 2016, 2016 World Conference on Futuristic Trends in Research and Innovation for Social Welfare (Startup Conclave).

[2]  Tingwen Huang,et al.  Neural Cryptography Based on Complex-Valued Neural Network , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Vinod Patidar,et al.  A Pseudo Random Bit Generator Based on Chaotic Logistic Map and its Statistical Testing , 2009, Informatica.

[4]  Mattia Frasca,et al.  A true random bit generator based on a memristive chaotic circuit: Analysis, design and FPGA implementation , 2019, Chaos, Solitons & Fractals.

[5]  Arindam Sarkar,et al.  Multilayer neural network synchronized secured session key based encryption in wireless communication , 2019, Indonesian Journal of Electrical Engineering and Computer Science.

[6]  J. K. Mandal,et al.  Secured Wireless Communication using Fuzzy Logic based High Speed Public-Key Cryptography (FLHSPKC) , 2012, ArXiv.

[7]  S. Santhanalakshmi,et al.  Analysis of Neural Synchronization Using Genetic Approach for Secure Key Generation , 2015, SSCC.

[8]  Zainab Khyioon Abdalrdha,et al.  Subject Review : Key Generation in Different Cryptography Algorithm , 2019 .

[9]  Mohammed M. Alani.  Applications of machine learning in cryptography: a survey , 2019, ICCSP.

[10]  Neeraj Kumar,et al.  An Efficient Spam Detection Technique for IoT Devices Using Machine Learning , 2021, IEEE Transactions on Industrial Informatics.

[11]  Yan Zhang,et al.  Blockchain and Federated Learning for Privacy-Preserved Data Sharing in Industrial IoT , 2020, IEEE Transactions on Industrial Informatics.

[12]  Miroslav Voznak,et al.  Security Verification of Artificial Neural Networks Used to Error Correction in Quantum Cryptography , 2018, 2018 26th Telecommunications Forum (TELFOR).

[13]  Lingfeng Liu,et al.  Pseudorandom bit generator based on non-stationary logistic maps , 2016, IET Inf. Secur..

[14]  K Lavanya,et al.  VECTORIZED NEURAL KEY EXCHANGE USING TREE PARITY MACHINE , 2019 .

[15]  Arindam Sarkar,et al.  Swarm Intelligence based Faster Public-Key Cryptography in Wireless Communication ( SIFPKC ) , 2012 .

[16]  Juan Li,et al.  Gravitational Search Algorithm with a New Technique , 2017, 2017 13th International Conference on Computational Intelligence and Security (CIS).

[17]  Shubham Mishra,et al.  An TPM Based Approach for Generation of Secret Key , 2019, International Journal of Computer Network and Information Security.

[18]  Subhendu Kumar Pani,et al.  Artificial Neural Synchronization Using Nature Inspired Whale Optimization , 2021, IEEE Access.

[19]  Wolfgang Kinzel,et al.  Neural cryptography , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[20]  Burak ÖzÇakmak,et al.  Neural and Quantum Cryptography in Big Data: A Review , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[21]  Dowon Hong,et al.  Neural Cryptography Based on Generalized Tree Parity Machine for Real-Life Systems , 2021, Secur. Commun. Networks.

[22]  Xin Yang,et al.  Semantic Learning Based Cross-Platform Binary Vulnerability Search For IoT Devices , 2021, IEEE Transactions on Industrial Informatics.

[23]  Muhammad Khurram Khan,et al.  Designing Anonymous Signature-Based Authenticated Key Exchange Scheme for IoT-Enabled Smart Grid Systems , 2020 .