ORTHOGONAL REGRESSED STEEPEST DESCENT DEEP PERCEPTIVE NEURAL LEARNING FOR IOT-AWARE SECURED BIG DATA COMMUNICATION

(Received: 30-Nov.-2022, Revised: 21-Jan.-2023 and 15-Feb.-2023 , Accepted: 19-Feb.-2023)

Authors S. L. Swapna, V. Saravanan,

Keywords #Big data #IoT #Multilayer deep perceptive neural learning #Orthogonal regression analysis #Szymkiewicz–Simpson coefficient #Maxout activation function #Steepest descent function

Abstract The Internet of Things (IoT) is a collection of interconnected intelligent devices that exist within the larger network known as the Internet. With the increasing popularity of IoT devices, massive data is generated day by day. The collected data needs to be continuously uploaded to the cloud server. Besides, the transmission of data in the cloud environment is performed via the Internet, which faces numerous threats. However, the security issue always lacks effective big data communication. Therefore, a novel technique called Orthogonal Regressed Steepest Descent Deep Structured Perceptive Neural Learning based Secured Data Communication (ORSDDSPNL-SDC) is introduced with higher accuracy and lesser time consumption. The ORSDDSPNL-SDC technique comprises three phases; namely, registration, user authentication, and secure data communication. In the ORSDDSPNL-SDC technique, the registration phase is carried out for creating a new ID and a password for each user in the cloud. The IoT device's data is then sent to a cloud server by the cloud user for storage. After that, the orthogonal regressed steepest descent multilayer deep perceptive neural learning is applied to examine the user_ ID with already registered ID based on Szymkiewicz–Simpson coefficient. Then, the Maxout activation function is to classify the user as authorized or unauthorized. Finally, the steepest descent function is applied for minimizing the classification error and increasing the classification accuracy. In this way, the authorized or unauthorized user is identified. Then, the secured communication is performed with the authorized cloud users. Experimental evaluation is carried out on the factors, such as classification accuracy, classification time and error rate, and space complexity for several users. The qualitative results and discussion indicate that the proposed ORSDDSPNL-SDC offers an elevated performance by achieving a higher classification accuracy and a minimum error as well as computation time when compared to the existing methods.

References

[1] H. Xie, Z. Zhang, Q. Zhang, S. Wei and C. Hu, "HBRSS: Providing High-secure Data Communication and Manipulation in Insecure Cloud Environments," Computer Comm., vol. 174, pp. 1-12, 2021.

[2] Q. Zhang, H. Zhong, W. Shi and L. Liu, "A Trusted and Collaborative Framework for Deep Learning in IoT," Computer Networks, vol. 193, pp. 1-10, DOI: 10.1016/j.comnet.2021.108055, 2021.

[3] Y. Li, Y. Zuo, H. Song and Z. Lv, "Deep Learning in Security of Internet of Things," IEEE Internet of Things Journal, vol. 9, no. 22, pp. 22133–22146, 2022.

[4] S. Zargar, A. Shahidinejad and M.Ghobaei-Arani, "A Lightweight Authentication Protocol for IoT-based Cloud Environment," Int. J. of Communication System, vol. 34, no.11, pp. 1-17, 2021.

[5] J. Shen, D. Liu, Q. Liu, X. Sun and Y. Zhang, "Secure Authentication in Cloud Big Data with Hierarchical Attribute Authorization Structure," IEEE Transactions on Big Data, vol. 7, no. 4, pp. 668 – 677, 2021.

[6] U. Iqbal, A. Tandon, S. Gupta, A. R. Yadav, R. Neware and F. W. Gelana, "A Novel Secure Authentication Protocol for IoT and Cloud Servers," Wireless Communications and Mobile Computing, vol. 2022, pp. 1-17, DOI: 10.1155/2022/7707543, 2022.

[7] A. Karati, R. Amin, S. K. H. Islam and K. R. Choo, "Provably Secure and Lightweight Identity-based Authenticated Data Sharing Protocol for Cyber-physical Cloud Environment," IEEE Transactions on Cloud Computing, vol. 9, no. 1, pp. 318 – 330, 2021.

[8] M. Wazid, J. Singh, A. K. Das, S. Shetty, M. K. Khan and J. J. P. C. Rodrigues, "ASCP-IoMT: AI-enabled Lightweight Secure Communication Protocol for Internet of Medical Things," IEEE Access, vol. 10, pp. 57990 – 58004, 2022.

[9] M. A. Jan, F. Khan, S. Mastorakis, M. Adil, A. Akbar and N.Stergiou, "LightIoT: Lightweight and Secure Communication for Energy-efficient IoT in Health Informatics," IEEE Transactions on Green Communications and Networking, vol. 5, no. 3, pp. 1202 – 1211, 2021.

[10] X. Lu, L. Yin, C. Li, C. Wang, F. Fang, C. Zhu and Z. Tian, "A Lightweight Privacy-preserving Communication Protocol for Heterogeneous IoT Environment," IEEE Access, vol. 8, pp. 67192–67204, DOI: 10.1109/ACCESS.2020.2978525, 2020.

[11] Z. Guan, W. Yang, L. Zhu, L.Wu and R.Wang, "Achieving Adaptively Secure Data Access Control with Privacy Protection for Lightweight IoT Devices," Science China Information Sciences, vol. 64, pp. 1-14, DOI: 10.1007/s11432-020-2957-5, 2021.

[12] F. M. Awaysheh, M. N. Aladwan, M. Alazab , S. Alawadi, J. C. Cabaleiro and T. F. Pena, "Security by Design for Big Data Frameworks Over Cloud Computing," IEEE Transactions on Engineering Management, vol. 69, no. 6, pp. 3676–3693, 2022.

[13] L. Atiewi, A. Al-Rahayfe, M. Almiani, S. Yussof, O. Alfandi, A. Abugabah and Y. Jararweh, "Scalable and Secure Big Data IoT System Based on Multifactor Authentication and Lightweight Cryptography," IEEE Access , vol. 8, pp. 113498 – 113511, DOI: 10.1109/ACCESS.2020.3002815, 2020.

[14] K. Thilagam, A. Beno, M. V. Lakshmi et al., "Secure IoT Healthcare Architecture with Deep Learning-based Access Control System," Journal of Nanomaterials, vol. 2022, pp. 1-8, DOI: 10.1155/2022/2638613, 2022.

[15] R. Li, H. Asaeda and J. Wu, "DCAuth: Data-centric Authentication for Secure In-network Big-data Retrieval," IEEE Transactions on Network Science and Engineering, vol. 7, no. 1, pp.15 – 27, 2020.

[16] U. Narayanan, V. Paul and S. Joseph, "A Novel System Architecture for Secure Authentication and Data Sharing in Cloud Enabled Big Data Environment," J. of King Saud Uni.-Computer and Information Sciences, vol. 34, no. 6, pp. 3121-3135, DOI: 10.1016/j.jksuci.2020.05.005, 2022.

[17] O. Kwabena, Z. Qin and T. Zhuang "MSCryptoNet: Multi-scheme Privacy-preserving Deep Learning in Cloud Computing," IEEE Access, vol. 7, pp. 29344–29354, DOI: 10.1109/access.2019.2901219, 2019.

[18] M. I. Ahmed and G. Kannan, "Secure End to End Communications and Data Analytics in IoT Integrated Application Using IBM Watson IoT Platform," Wireless Personal Communications, vol. 120, pp.153–168, DOI: 10.1007/s11277-021-08439-7, 2021.

[19] T. Maitra, S. Singh, R. Saurabh and D. Giri, "Analysis and Enhancement of Secure Three-factor User Authentication Using Chebyshev Chaotic Map," J. of Inf. Security and Appli., vol.61, pp.1-13, 2021.

[20] J. Sun, H. Xiong, X. Liu, Y. Zhang, X. Nie and R. H. Deng, "Lightweight and Privacy-aware Fine-grained Access Control for IoT-oriented Smart Health," IEEE IoT J., vol. 7, no. 7, pp. 6566- 6575, 2020.

[21] L. Zhang, Y. Shi, Y. Chang and C. Lin, "Hierarchical Fuzzy Neural Networks with Privacy Preservation for Heterogeneous Big Data," IEEE Transactions on Fuzzy Systems, vol. 29, no. 1, pp. 46–58, 2021.

[22] S. Banerjee, S. Roy, V. Odelu et al., "Multi-authority CP-ABE-based User Access Control Scheme with Constant-size Key and Ciphertext for IoT Deployment," J. of Information Security and Applications, vol. 53, pp. 1-22, DOI: 10.1016/j.jisa.2020.102503, 2020.

[23] S. Xu, Y. Li, R. H. Deng, Y. Zhang, X. Luo and X. Liu "Lightweight and Expressive Fine-grained Access Control for Healthcare Internet-of-Things," IEEE Transactions on Cloud Computing, vol. 10, no. 1, pp. 474–490, 2022.

[24] P. Abirami and S. V.Bhanu, "Enhancing Cloud Security Using Crypto-deep Neural Network for Privacy Preservation in Trusted Environment," Soft Computing, vol. 24, pp. 18927–18936, DOI: 10.1007/s00500-020-05122-0, 2020.

[25] S.Atiewi, A. Al-Rahayfeh, MuderAlmiani et al., "Scalable and Secure Big Data IoT System Based on Multifactor Authentication and Lightweight Cryptography," IEEE Access, vol. 8, pp. 113498–113511, DOI: 10.1109/ACCESS.2020.3002815, 2020.

Abstract: The Internet of Things (IoT) is a collection of interconnected intelligent devices that exist within the larger network known as the Internet. With the increasing popularity of IoT devices, massive data is generated day by day. The collected data needs to be continuously uploaded to the cloud server. Besides, the transmission of data in the cloud environment is performed via the Internet, which faces numerous threats. However, the security issue always lacks effective big data communication. Therefore, a novel technique called Orthogonal Regressed Steepest Descent Deep Structured Perceptive Neural Learning based Secured Data Communication (ORSDDSPNL-SDC) is introduced with higher accuracy and lesser time consumption. The ORSDDSPNL-SDC technique comprises three phases; namely, registration, user authentication, and secure data communication. In the ORSDDSPNL-SDC technique, the registration phase is carried out for creating a new ID and a password for each user in the cloud. The IoT device's data is then sent to a cloud server by the cloud user for storage. After that, the orthogonal regressed steepest descent multilayer deep perceptive neural learning is applied to examine the user_ ID with already registered ID based on Szymkiewicz–Simpson coefficient. Then, the Maxout activation function is to classify the user as authorized or unauthorized. Finally, the steepest descent function is applied for minimizing the classification error and increasing the classification accuracy. In this way, the authorized or unauthorized user is identified. Then, the secured communication is performed with the authorized cloud users. Experimental evaluation is carried out on the factors, such as classification accuracy, classification time and error rate, and space complexity for several users. The qualitative results and discussion indicate that the proposed ORSDDSPNL-SDC offers an elevated performance by achieving a higher classification accuracy and a minimum error as well as computation time when compared to the existing methods.
URL: https://jjcit.org/paper/188

,abstract={The Internet of Things (IoT) is a collection of interconnected intelligent devices that exist within the larger network known as the Internet. With the increasing popularity of IoT devices, massive data is generated day by day. The collected data needs to be continuously uploaded to the cloud server. Besides, the transmission of data in the cloud environment is performed via the Internet, which faces numerous threats. However, the security issue always lacks effective big data communication. Therefore, a novel technique called Orthogonal Regressed Steepest Descent Deep Structured Perceptive Neural Learning based Secured Data Communication (ORSDDSPNL-SDC) is introduced with higher accuracy and lesser time consumption. The ORSDDSPNL-SDC technique comprises three phases; namely, registration, user authentication, and secure data communication. In the ORSDDSPNL-SDC technique, the registration phase is carried out for creating a new ID and a password for each user in the cloud. The IoT device's data is then sent to a cloud server by the cloud user for storage. After that, the orthogonal regressed steepest descent multilayer deep perceptive neural learning is applied to examine the user_ ID with already registered ID based on Szymkiewicz–Simpson coefficient. Then, the Maxout activation function is to classify the user as authorized or unauthorized. Finally, the steepest descent function is applied for minimizing the classification error and increasing the classification accuracy. In this way, the authorized or unauthorized user is identified. Then, the secured communication is performed with the authorized cloud users. Experimental evaluation is carried out on the factors, such as classification accuracy, classification time and error rate, and space complexity for several users. The qualitative results and discussion indicate that the proposed ORSDDSPNL-SDC offers an elevated performance by achieving a higher classification accuracy and a minimum error as well as computation time when compared to the existing methods.},
keywords={Big data,IoT,Multilayer deep perceptive neural learning,Orthogonal regression analysis,Szymkiewicz–Simpson coefficient,Maxout activation function,Steepest descent function},
ISSN={2413-9351},
month={March}}

AB - The Internet of Things (IoT) is a collection of interconnected intelligent devices that exist within the larger network known as the Internet. With the increasing popularity of IoT devices, massive data is generated day by day. The collected data needs to be continuously uploaded to the cloud server. Besides, the transmission of data in the cloud environment is performed via the Internet, which faces numerous threats. However, the security issue always lacks effective big data communication. Therefore, a novel technique called Orthogonal Regressed Steepest Descent Deep Structured Perceptive Neural Learning based Secured Data Communication (ORSDDSPNL-SDC) is introduced with higher accuracy and lesser time consumption. The ORSDDSPNL-SDC technique comprises three phases; namely, registration, user authentication, and secure data communication. In the ORSDDSPNL-SDC technique, the registration phase is carried out for creating a new ID and a password for each user in the cloud. The IoT device's data is then sent to a cloud server by the cloud user for storage. After that, the orthogonal regressed steepest descent multilayer deep perceptive neural learning is applied to examine the user_ ID with already registered ID based on Szymkiewicz–Simpson coefficient. Then, the Maxout activation function is to classify the user as authorized or unauthorized. Finally, the steepest descent function is applied for minimizing the classification error and increasing the classification accuracy. In this way, the authorized or unauthorized user is identified. Then, the secured communication is performed with the authorized cloud users. Experimental evaluation is carried out on the factors, such as classification accuracy, classification time and error rate, and space complexity for several users. The qualitative results and discussion indicate that the proposed ORSDDSPNL-SDC offers an elevated performance by achieving a higher classification accuracy and a minimum error as well as computation time when compared to the existing methods.

Download Full Text