Intrusion Detection Using Anomaly Detection Algorithm and Snort

Many organizations and businesses are all delving into crafting out an online presence for themselves. This could either be in the form of websites or mobile apps. Many advantages come from an online presence; however, there are some drastic disadvantages that, if left unchecked, could disrupt any business or organization. Chief amongst these disadvantages is the aspect of security. However, many of the techniques that some organizations utilize to guard against unwanted access have been inadequate, and as a result, many unauthorized system break-ins have been reported. This is not made any better by the fact that certain applications used in hacking or system breach are now commonplace. Therefore, the focus of this work is to take an Intrusion Detection System (IDS) for a local network to detect network intrusion. A statistical approach, as well as a binomial classification, was used for simplicity in classification. The result shows the outlier value for each item considered; a 1 depicts an attack, a 0 depicts normalcy. The results are promising in dictating intrusion and anomalies in an IDS system