A Comprehensive Survey on Intrusion and Fraud Detection in Data Mining

Abstract

Intrusions are any set of actions that threatens the integrity, availability, or confidentiality of a network resource. Intrusion detection is an essential and important technique in data mining field. Fraud can be defined as an intentional deception or misrepresentation that an individual knows to be false that results in some unauthorized benefit to himself or another person. Due to the dramatic increase of fraud which results in loss of billions of dollars worldwide each year, several modern techniques in detecting fraud are continually evolved and applied to many business fields. Fraud detection involves monitoring the behaviour of populations of users in order to estimate, detect, or avoid undesirable behaviour. Undesirable behaviour is a broad term including misbehaviour; fraud intrusion, and account defaulting. Intrusion and fraud detection complements preventive mechanisms such as firewalls and OS-security. This survey paper categorises, compares, and summarises details from published technical and review articles in intrusion and fraud detection. It defines the professional fraudster, formalises the main types and subtypes of known fraud. The goal of this paper is to provide a comprehensive survey of different techniques to detect intrusion and frauds.