Cloud Services Anomalies Detection Using Network Flowdata Analysis

Main Article Content

Sreenivasa Chakravarthi Sangapu, R. Jagadeesh Kannan, V. Anantha Natarajan

Abstract

Cloud computing paved an excellent platform for the emergence of cost effective technological solutions. However, security and privacy issues still remain as a stringent challenge during service catering. Explicitly, the service utility anomalies are liable to cause severe privacy and security issues in cloud service delivery. So, the overall performance of Cloud service consumption and end-user applications’ service levels utility is degraded. The open access and distributed nature of the cloud computing is the major reason for its vulnerability to intruders. The security and privacy in cloud services have many challenges and problems still open for research. This paper proposes an intrusion detection method capable of detecting nine categories of attacks in two stages.  This paper focuses on establishing a network based intrusion detection mechanism using machine learning techniques. A model will be constructed with a supervised learning methodology using historical network flowdata and flowdata collected from Internet.

Article Details

Section
Articles