Towards the Development of a Cloud Computing Intrusion Detection Framework Using an Ensemble Hybrid Feature Selection Approach

Attacks on cloud computing (CC) services and infrastructure have raised concerns about the efficacy of data protection mechanisms in this environment. The framework developed study (CCAID: computing, attack, intrusion detection) aims to improve performance detection systems (IDS) operating CC environments. It deploys a proposed new hybrid ensemble feature selection (FS) method. includes FS algorithms three different types (filter, wrapper, embedded algorithms). selected features used train ML (machine learning) model component comprised binary engine for identification malicious/attack packets multiclassification type attack. Both engines deploy classifiers. Experiments were carried out using NSL KDD dataset. achieved classification accuracy 99.55% with very low false alarm rate 0.45%. was also high (98.92%). These results compare favourably reported literature indicate feasibility implementation.