A Novel RDAE Based PSR-QKD Framework for Energy Efficient Intrusion Detection

Abstract

Wireless Sensor Networks (WSN), which collect a large amount of confidential data related to the activities of the user, have emerged as a promising research platform recently. The main purpose of ambient intelligence might be easily damaged by an attacker tampering with those kinds of data. Hence, it is significant to secure the data. In the existing intrusion detection techniques, due to single-time authentication, the robustness level is low; thus, if any high-level attack occurs, there is a chance of skipping them. So, a novel R-Distributed Auto-Encoder (RDAE)-based Pseudo Random number based Quantum Key Distribution (PSR-QKD) is employed for energy-efficient intrusion detection to overcome the limitations. Initially, the node initialization is done and the original ID is assigned to them. By employing K-Nearest Neighbour (KNN) algorithm, the clustering is performed. Then, by deploying Double Precision Integrated-Golden Tortoise Beetle Optimizer (DPI-GTBO), the cluster heads are selected. For acquiring the unique ID, the original ID of the CH is hashed by RIPE Message Digest (RIPEMD)-128. By using the PSR-QKD technique, key generation is performed in the server. The Base Station (BS) verifies the node based on trust value and shares the public key during a new node entry. By employing RDAE, the CH matches the public key with the server and performs attack detection. In the end, CH shares the private key with the non-malicious nodes. When analogized to the prevailing methodologies, the proposed method is found to be more efficient.