Self-Attention conditional generative adversarial network optimised with crayfish optimization algorithm for improving cyber security in cloud computing

Abstract

The decentralized and distributed architecture of cloud computing promotes adoption and growth in various societal domains, including education, government, information technology, business, entertainment. Cloud computing (CC) makes a broad range of information technologies available. Security and privacy are key challenges in storing big data in the cloud. To overcome this challenge, a Self-Attention Conditional Generative Adversarial Network Optimised with Crayfish Optimization Algorithm for Improving Cyber Security in Cloud Computing (CybS-CC-SACGANCOA) is proposed in this paper to enhance the safety of CC environment. The input data is amassed from NSL-KDD database. After that, the data is fed to pre-processing segment. The segment of pre-processing eliminates Cloud data termination and missing value replacement using Reformed Phase Conserving Vibrant Range Compression filter. The results of pre-processing serves for feature selection. The optimal features are selected by means of Manta Ray Foraging Optimization Algorithm (MRFOA). Cloud data is categorized as normal and abnormal data, like Denial-of-Service (DoS), Probe, Remote to local attack (R2L), User to root attack (U2R) by the help of SACGAN. Crayfish Optimization Algorithm (COA) is proposed to optimize the SACGAN classifier that classifies anomaly data precisely. The proposed CSCC-SACGANCOA technique is activated in Python under some metrics. The proposed CSCC-SACGANCOA approach has attained higher detection accuracy, lower computation time, higher AUC, higher scalability and lower detection error rate compared to the existing methods.