IMPROVED LIGHTWEIGHT CRYPTOGRAPHY ALGORITHM USING MACHINE LEARNING APPROACH ON IoT PLATFORM

Abstract

The next era technology in the Internet connectivity is none other than Internet of Things (IoT). It connects various homogenous and heterogeneous physical objects that interact among themselves without human intervention. I-networking, security plays a significant role in preventing unauthorized access, information misuse, tracking and security, reliability and accurate transmission of information, performance factors, etc. In the present scenario, there is a requirement for basic security standards such as confidentiality, integrity and reliability. The increased number of connected devices have raised the quantity of data generated; this raises concerns about data security. Also collected data from autonomous sensors may have security threat on its travel to reach the IoT cloud platform. In order to overcome these problems, this research work proposes the application of heuristic-algorithm-based lightweight cryptography on IoT platforms which has been used to improve the security and reliability of the system. This Improved lightweight cryptography approach to IoT-based technology allows communication between networked smart objects to be safe and effective. The experimental validation of the proposed method in comparison with traditional methods such as Characteristics Based Encryption (CBE), Key Policy Characteristic Based Encryption (KP-CBE), Fuzzy Identity-Based Encryption-enabled-Full Security (FIBEFS) and Cipher Text (CP-ABE) method shows promising outcomes. The experimental results have been analyzed in terms of energy, performance, accuracy, stability, precision and error rate.