In the era of digital revolution, a huge amount of data is being
generated from different networks on a daily basis. Security of this
data is of utmost importance. Intrusion Detection Systems are found to
be one the best solutions towards detecting intrusions. Network
Intrusion Detection Systems are employed as a defence system to secure
networks. Various techniques for the effective development of these
defence systems have been proposed in the literature. However, the
research on the development of datasets used for training and testing
purpose of such defence systems is equally concerned. Better datasets
improve the online and offline intrusion detection capability of
detection model. Benchmark datasets like KDD 99 and NSL-KDD cup 99
obsolete and do not contain network traces of modern attacks like Denial
of Service, hence are unsuitable for the evaluation purpose. In this
work, a detailed analysis of CIDDS-001 dataset has been done and
presented. We have used different well-known machine learning techniques
for analysing the complexity of the dataset. Eminent evaluation metrics
including Detection Rate, Accuracy, False Positive Rate, Kappa
statistics, Root mean squared error have been used to show the
performance of employed machine learning techniques.