查看文章

Anomaly detection in specific datasets involves the detection of circumstances that are common in a homogeneous data. When looking at network traffic data, it is generally difficult to determine the type of attack without proper analysis and this holds true when simply viewing a record of network traffic with thousands of internet users to detect malicious activity. However, there are different types of datasets in light of the way they record or acquire data and facts. The paper aims to compare and analyse multiple datasets including NSL-KDD and MAWI by using K-means clustering algorithm. Specifically, the paper analyses the blind-Spots of the datasets and evaluates the most suitable dataset for K-means clustering algorithm. This paper’s quantitative data analysis results are helpful in evaluating weaknesses of each dataset of traffic data, when using K-means clustering algorithm.