Detection of Unauthorized Users to Secure the Sensitive Medical Data Using Machine Learning Method

Abstract

A network unauthorized accessof users refers to any action that takes place without permission on a computer network. Such undesired actions consume the network resources and threaten the security of the network. An intruder is a person who gains unauthorized access to a system, to damage the system, or to disturb medical data on that system. Generally, the objective of an intruder is to gain access to a system or to increase the range of privileges accessible on a system. Unauthorized access can be caused by outsiders who access the systems from the Internet, insiders or authorized users who seek to procure additional privileges and by authorized users who misemploy the privileges granted to them. Outsiders are adversaries with no direct access to the nodes in a network, but may have access to the physical medium. Malicious activities executed on a network or a computer system, by persons with authorized system access are called insider attacks. Insiders are usually disgruntled employees who have a grudge on the company. The Machine Learning based Unauthorized Access Detection System (ML-UADS) identifies the nodes causing outliers and then remove such kind of nodes by using trained medical data.In this research work, for keen monitoring on the network to detect unauthorized users a machine learning technique is proposed to provide security to the medical data and avoids unauthorized access more accurately. The proposed method is compared with the traditional methods and the results show that the proposed method detects unauthorized users accurately.