Efficient Intrusion Detection in Cloud Environments Using Optimized Sparse and Contractive Autoencoders

ABSTRACT In recent years, cloud computing has gained enormous development in computing systems. The cloud computing environment provides diverse benefits to its cloud users via the internet including storage, applications, on‐demand services, etc. Nowadays, it has been accepted and utilized by various companies for uploading their massive amounts of data to a cloud platform. As a result, various cloud computing‐based IDS (CIDS) techniques are developed to prevent a cloud network from attacks and protect the data from internal and external anomalous activities. Despite that, security and privacy concerns remain a significant challenge, which demands an effective methodology to ensure user confidentiality and integrity. Thus, we proposed a Stacked Convolutional and Recurrent Contractive Sparse Autoencoder (SCRCS‐AE) and Levy flight and reconstructed mathematical optimization acceleration‐based Arithmetic Optimization Algorithm (LRMOA‐AOA) for an efficient ID in a cloud environment. In this paper, we stack three SCRCS‐AE blocks to extract their features. A single SCRCS‐AE block involves a convolutional encoder and recurrent decoder to capture long‐term dependencies and rebuild input in forward and reverse directions for excellent feature extraction and classification of different intrusions. The integration of sparse and contractive loss is deployed to extract high‐dimensional data features to boost the SCRCS‐AE model's generalizability and robustness. The LRMOA‐AOA optimization algorithm integrates a Levy flight distribution and arithmetic optimization algorithm (AOA) approach that tunes the hyperparameters to enhance the efficacy of the SCRCS‐AE. The proposed SCRCS‐AE achieved 98.73% accuracy, 98.46% detection rate, 1.27% false alarm rate, and 98.61% precision on the UNSW‐NB15 dataset and attained 97.93% accuracy, 97.74% detection rate, 2.07% false alarm rate, and 97.59% precision on the NSL‐KDD dataset. These superior outcomes show that the proposed SCRCS‐AE technique works well on CIDS in detecting diverse assaults with higher detection rates and lower false alarm rates to strengthen cloud network security and privacy.