Journal
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
Volume 24, Issue 1, Pages 393-415Publisher
SPRINGER
DOI: 10.1007/s10586-020-03120-3
Keywords
Attack detection; Cluster center; Denial of service attacks; Feature extraction; Mahalanobis distance; Statistical method
Ask authors/readers for more resources
The paper proposes a class center based triangle area vector (CCTAV) method for DoS attack detection, which reduces the complexity of feature extraction and enhances attack detection accuracy by computing the mean of target classes and extracting correlations between features. The proposed method is evaluated using tenfold cross validation and demonstrates significant results compared to existing attack detection methods.
Denial of service (DoS) attack is the menace to private cloud computing environment that denies services provided by cloud servers leading to huge business losses. Efficient DoS attack detection mechanisms are demanded which necessitates the extraction of features for its best performance. The lacuna in the existing feature extraction based detection systems is the sensitiveness of initial cluster center which leads to high false alarm rate and low accuracy. In this paper, this issue is addressed by proposing a class center based triangle area vector (CCTAV) method which computes the mean of target classes individually and extracts the correlation between features. Mahalanobis distance measure is used for profile construction and DoS attacks detection. The proposed CCTAV method is tested with five publicly available datasets and compared with existing methods. It is noticed that the proposed statistical method reduces the complexity of feature extraction and enhances the attack detection process. The proposed approach is evaluated by conducting tenfold cross validation to compute 95% confidence interval. It is evident that the accuracy obtained for all the datasets are within the confidence interval. Further, the proposed CCTAV method provides significant results compared to the state-of-the-art attack detection methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available