Economic Denial of Sustainability Attack Detection Using Machine Learning
Md Sharafat Hossain, Md Saiful Islam · 2023
Cloud computing stands as one of the most pervasive technological innovations, providing computing services, including IT infrastructure, over the internet. This technology alone saves many small and medium-sized IT companies from the significant expense of building their IT infrastructure at the beginning of their business journey. Cloud computing offers various user-friendly features, including scalability and flexibility, with a pay-as-you-go model. However, these features come with some drawbacks along with their benefits. Among the challenges posed by the flexibility and pay-as-you-go attributes of cloud computing, one of the most detrimental threats is Economic Denial of Sustainability (EDoS), leading to significant financial losses for consumers of cloud services. Consequently, an effective and efficient solution is urgently needed to fully realize the benefits of cloud computing. In this research, we aim to address the EDoS attack using machine learning-based methods. Our research is conducted on the UNSW-NB15 dataset, and the result demonstrates that our optimized LightGBM model with chosen hyperparameters surpasses existing models with significant improvements in attack detection, achieving a recall score of 99.21%.