Identification of authorship and prevention of fraudulent transactions/cybercrime using efficient high performance machine learning techniques
by B.J. Sowmya; R. Hanumantharaju; D. Pradeep Kumar; K.G. Srinivasa
International Journal of Business Intelligence and Data Mining (IJBIDM), Vol. 22, No. 1/2, 2023

Abstract: Cyber safety is the best skill required among a group of employees in organisations. Many offenders hide behind anonymous masking, including dishonest purchases, brazen plagiarism of the work, breaching corporate safety and stealing private data. To understand and analyse the actual phenomenon encountered with data, requirements of scientific methods, machine learning techniques, processes are to be used. This paper aims to tackle these problems by providing a protection layer for users, where data is being gathered from cyber security sources, analytical complement with latest data-driven patterns provides effective security solutions. We then discuss machine learning, deep learning powered models for the detection of insider threats and identifying authorship identification of anonymised articles. The individual modules are trained on authorship attribution, mouse monitoring, keyboard monitoring and command tracing and reached promising results with good accuracies in the range of 65%-85% on average.

Online publication date: Wed, 30-Nov-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Business Intelligence and Data Mining (IJBIDM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com