DoS Attack Detection System Using Multivariate Correlation Analysis(MCA) and Classification Techniques

Abstract

Denial-of- Service (DoS) attacks cause serious impact on these computing systems. For detecting common specific operations of the denial of service attacks with proceedings of detection in distributed service attacks in networks. Recently use Multivariate Correlation Analysis (MCA) for accurate network traffic characterization by extracting the geometrical correlations between network traffic features. Our MCA-based DoS attack detection system employs the principle of anomaly-based detection in attack recognition. This makes our solution capable of detecting known and unknown DoS attacks effectively by learning the patterns of legitimate network traffic only. The sudden increase in traffic can cause the server to offer degraded performance. My Doom devastation on Microsoft, wiki leaks encounter with DoS barrages are some examples to highlight the impact. And other major Internet players like Amazon, CNN, and Yahoo are no exception. Early discovery of these attacks, although challenging, is necessary to protect victim server's network infrastructure resources. Previous intrusion prevention systems like MCA although efficient in thwarting DoS, its architecture is based on ISP collaboration and virtual protection rings. We propose to use an IPS rules (Classification rules) driven DoS detection approach that checks various parts of a data packet and not just the header. This enables the detection system to eliminate other forms DoS attacks such as Slow Read DoS attack. Its effectiveness and low overhead, as well as its support for incremental deployment in real networks are demonstrated.