User Behavior Analysis to Detect Insider Threat by Using Machine Learning Algorithms

Insider threats, in which someone within an organization poses a risk, are widely regarded as the most dangerous in cybersecurity. Many analysts are working hard to identify and prevent these risks. However, the most difficult aspect of cybersecurity is determining which computers and users are affected. These computers are connected to servers or monitored by them, but there are no clear indications that attackers are targeting specific users. It is critical for the organization to defend against both internal and external cyberattacks. Cyber security measures should be up to date is critical for protecting our organizations. External threats can be identified easily but to identify insider threats is a complex task. Recently, there has been an increased emphasis on computer security, particularly in developing internal risk detection systems. Artificial intelligence, Internet of Things, distributed computing, data mining, portable ledgers, and data discovery are some of the advanced methods that have gained popularity for mitigating insider risk. Each of these approaches is unique and takes insider threats into account to a varying degree. In this paper, we use different machine learning models to find out the insiders.