Heuristically enhanced multi-head attention based recurrent neural network for denial of wallet attacks detection on serverless computing environment

Denial of Wallet (DoW) attacks are a cyber threat designed to utilize and deplete an organization's financial resources by generating excessive prices or charges in their cloud computing (CC) and serverless computing platforms. These threats are primarily appropriate in serverless manners because of features such as auto-scaling, pay-as-you-go, restricted control, and cost growth. Serverless computing, frequently recognized as Function-as-a-Service (FaaS), is a CC method that permits designers to construct and run uses without the requirement to accomplish typical server structure. Detecting DoW threats involves monitoring and analyzing the system-level resource consumption of specific bare-metal mechanisms. Efficient and precise detection of internal DoW threats remains a crucial challenge. Timely recognition is significant in preventing potential damage, as DoW attacks exploit the financial model of serverless environments, impacting the cost structure and operational integrity of services. In this study, a Multi-Head Attention-based Recurrent Neural Network for Denial of Wallet Attacks Detection (MHARNN-DoWAD) technique is developed. The MHARNN-DoWAD method enables the detection of DoW attacks on serverless computing environments. At first, the presented MHARNN-DoWAD model performs data preprocessing by using min-max normalization to convert input data into constant format. Next, the wolf pack predation (WPP) method is employed for feature selection. The detection and classification of DoW attacks, the multi-head attention-based bi-directional gated recurrent unit (MHA-BiGRU) model is utilized. Eventually, the improved secretary bird optimizer algorithm (ISBOA)-based hyperparameter choice process is accomplished to optimize the detection results of the MHA-BiGRU model. A comprehensive set of simulations was conducted to demonstrate the promising results of the MHARNN-DoWAD method. The experimental validation of the MHARNN-DoWAD technique portrayed a superior accuracy value of 98.30% over existing models.