Big Data Distributed Support Vector Machine

Abstract

 Data mining and machine learning (ML) methods are being used more than ever before in cyber security. The use of machine learning (ML) is one of the potential solutions that may be successful against zero day attacks, starting with the categorization of IP traffic and filtering harmful traffic for intrusion detection. In this field, certain published systematic reviews were taken into consideration. Contemporary systematic reviews may incorporate both older and more recent works in the topic of investigation. All of the papers we looked at were thus recent. Data from 2016 to 2021 were utilized in the study. Both security professionals and hackers use data mining capabilities. Applications for data mining may be used to analyze programme activity, surfing patterns, and other factors to identify potential cyber-attacks in the future. Utilizing statistical traffic features, ML, and data mining approaches, new study is being conducted. This research conducts a concentrated literature review on machine learning and its usage in cyber analytics for email filtering, traffic categorization, and intrusion detection. Each approach was identified and a summary provided based on the relevancy and quantity of citations.  Some well-known datasets are also discussed since they are a crucial component of ML techniques. On when to utilize a certain algorithm is also offered some advice. On MODBUS data gathered from a gas pipeline, four ML algorithms have been evaluated. Using ML algorithms, different assaults have been categorized, and then the effectiveness of each approach has been evaluated. This study demonstrates the use of ML and data mining for threat research and detection, with a focus on malware detection with high accuracy and short detection times.