HIDM: A Hybrid Intrusion Detection Model for Cloud Based Systems

The cloud computing model is very popular among the users in different sectors like banking, healthcare, education etc due to its customized low-cost services with high level reliability with efficiency. Since the cloud services are accessed through the internet by various types of users, therefore the security is a major concern in cloud based system. Network attackers can cause damage to the system through intrusive acts such as denial of service attack, backdoor channel attack etc. One strategy to stop this kind of attack and safeguard the system is to use intrusion detection model. Most of the intrusion detection models can only identify known attacks with less efficiency. But most of them are unable to detect unknown attacks which are apparently new and recycled threats. Thus a network intrusion detection model is required in cloud based systems that can identify known as well as unknown attacks. In this research work, a hybrid intrusion detection model has been introduced for cloud based systems which can uses signature based detection as well as anomaly based detection in a combined way to detect all types of attack. The experiments are performed on UNSW-NB15, CICIDS2017 and NSL-KDD datasets to get the model performance and found that it has high detection rate 92.7% on UNSW-NB15, 85.1% on CICIDS dataset and 99.8% on NSL-KDD dataset. The comparative analysis of the proposed model shows that the model performance is better than some existing models.

Automated summary

The cloud computing model is widely popular, but security is a major concern. This research introduces a hybrid intrusion detection model for cloud based systems, combining signature-based detection and anomaly-based detection to detect known and unknown attacks. The experiments show high detection rates for the proposed model compared to existing models.