With the ubiquitous computing of providing services and applications atanywhere and anytime, cloud computing is the best option as it offers flexibleand pay-per-use based services to its customers. Nevertheless, security andprivacy are the main challenges to its success due to its dynamic anddistributed architecture, resulting in generating big data that should becarefully analysed for detecting network vulnerabilities. In this paper, wepropose a Collaborative Anomaly Detection Framework CADF for detecting cyberattacks from cloud computing environments. We provide the technical functionsand deployment of the framework to illustrate its methodology of implementationand installation. The framework is evaluated on the UNSW-NB15 dataset to checkits credibility while deploying it in cloud computing environments. Theexperimental results showed that this framework can easily handle large-scalesystems as its implementation requires only estimating statistical measuresfrom network observations. Moreover, the evaluation performance of theframework outperforms three state-of-the-art techniques in terms of falsepositive rate and detection rate.
展开▼
