Stochastic Quantum Bolt-Belief Neural Network-Based Insrusion Detection With Two-Fish Digital Hash Cryptography for Data Security

Abstract

Ensuring the security of wireless data transmission is a crucial element of intrusion detection systems (IDS) that rely on deep learning and cryptography. Therefore, this study introduces the stochastic quantum bolt-belief neural network (SQB-BNN) and two-fish digital hash cryptography (TFDC). The dataset was first preprocessed using the ProScalar Splash normalisation approach. Subsequently, the Qubit Lion optimisation algorithm (QLOA) is used to extract the attack-related characteristics. The stochastic quantum bolt-belief neural network assists in accurately detecting intruders. Finally, Two-Fish digital hash cryptographic technique ensures the secure storage of data files on the server. The whole experiment was conducted with the KDD Cup dataset under MATLAB environment. Therefore, the research has shown that the proposed method enhanced data storage security by effectively addressing security issues.