Feasibility of Supervised Machine Learning for Cloud Security

TL;DR

This paper evaluates the feasibility of supervised machine learning models for cloud security by training on one dataset and testing on another to assess robustness across different environments.

Contribution

It demonstrates the importance of cross-dataset testing for machine learning models in cloud security and highlights the need for more comprehensive research in this area.

Findings

Models trained on UNSW dataset tested on ISOT dataset show varying performance.

Cross-dataset evaluation reveals robustness issues in current machine learning approaches.

More research is needed to improve model generalizability across diverse cloud environments.

Abstract

Cloud computing is gaining significant attention, however, security is the biggest hurdle in its wide acceptance. Users of cloud services are under constant fear of data loss, security threats and availability issues. Recently, learning-based methods for security applications are gaining popularity in the literature with the advents in machine learning techniques. However, the major challenge in these methods is obtaining real-time and unbiased datasets. Many datasets are internal and cannot be shared due to privacy issues or may lack certain statistical characteristics. As a result of this, researchers prefer to generate datasets for training and testing purpose in the simulated or closed experimental environments which may lack comprehensiveness. Machine learning models trained with such a single dataset generally result in a semantic gap between results and their application. There is a dearth of research work which demonstrates the effectiveness of these models across multiple datasets obtained in different environments. We argue that it is necessary to test the robustness of the machine learning models, especially in diversified operating conditions, which are prevalent in cloud scenarios. In this work, we use the UNSW dataset to train the supervised machine learning models. We then test these models with ISOT dataset. We present our results and argue that more research in the field of machine learning is still required for its applicability to the cloud security.