Behavioural analysis approach for IDS based on attack pattern and risk assessment in cloud computing

Cloud environments are becoming easy targets for intruders looking for possible vulnerabilities to exploit as many enterprise applications and data are moving into cloud platforms. The use of current generation of IDS have various limitations on their performance making them not effective for cloud computing security and could generate a huge number of false positive alarms. Analysing intrusion based on attack patterns and risk assessment has demonstrated its efficiency in reducing the number of false alarms and optimising the IDS performances. However, the use of the same value of likelihood makes the approach lacks of real risk value determination. This paper intended to present a new probabilistic and behavioural approach for likelihood determination to quantify attacks in cloud environment, with the main task to increase the efficiency of IDS and decrease the number of alarms. Experimental results show that our approach is superior to the state-of-the-art approaches for intrusion detection in cloud.