Analysis and Evaluation of Integrated Cyber Crime Offences

Abstract

Cyber Crime is an illegal activity in which offender makes use of the smart devices such as computers and other network devices as the primary source in order to gain some profit from the victim by violating the rules. Cyber attacks are persistently rising, detection of cyber crimes and providing preventive measures by manual investigation are often failed to control the cyber attacks. Therefore, machine learning plays a vital role in detecting those cybercrimes. It has the ability to detect and analyze the cyber attack and provides the preventive measures in order to reduce the incarnation of the cyber crimes. Therefore, incorporating machine learning techniques such as classification and clustering into our framework can help to build a cyber crime detection system and prediction of cyber attacks annually. Existing literature in the area of cybercrime offences by feature extraction focuses on several techniques. In this a novel framework for cybercrime offences by feature extractions is proposed. In this proposed framework one can upload any unstructured cyber crime report to generate the structure data through TFID technique. Later this framework can give a report on categorization and resolution of the cyber crime offences (especially ID theft, Hacking and Copyright attacks) by its severity and occurrence. It is achieved by extracting the feature description using text mining algorithms and by using the performance measurements and prediction analysis of cyber crime.