An Assessment of Big Data Analytics for Cyber-threats Detection
TNOU N.Sivashanmugam · International Journal of Advances in Engineering and Management · 2025
Traditional infiltration detection systems separate the alarm and focus on low-level dangers. Due to several alerts obtained each day. Since human users should make a lot of effort, it is almost difficult to fully examine each alarm message. Analysis of historical data and looking for abnormalities that depart from the ideal detect discrepancy. The advantage is that it can identify unknown attacks. Many systems to detect discrepancies depend on data mining methods. However, these abilities rarely live with various forms of the attack and technologies that develop rapidly. However, keeping in mind human aspects in the identity of discrepancy, we get a chance to increase the current algorithm and provide better results. Snort is the actual industry standard and a reliable, proven system technology. In previous research, snort log data was not used to compare methods of detecting various discrepancy. Snort log data analysis software is already widely available; However these programs are purely visualization tools and do not use data mining techniques. Using Big Data Analytics, heteMSD is an outline to identify targeted cyber attacks. The name of the recommended framework is asymmetrical multi -level data. There should be a strong structure that can assist security analysts to reduce the blindness of data analysis from several data sources without reducing the level of digital safety assurance. A correlation engine can reduce the alert volume, while analyzing a log resource by grouping multiple warnings, which is a part of the ongoing attack. Alert threading is the word for this process. In the case of odd log resources, a correlation engine should be able to determine whether the report from many logs is related to the same incident.