A Comparative Study of the Most Important Methods for Forecasting the ICT Systems Vulnerabilities

Abstract

Nowadays, companies are facing plenty of IT secure attacks and to guarantee safe, untroubled, and continuous functioning of their business, they should detect and forecast the volume of IT security vulnerabilities and be prepared for future threats. The aim of this paper is to present a comparative study of the most important and promising methods for forecasting the ICT systems vulnerabilities.

Forecasting the Number of Bugs and Vulnerabilities in Software Components Using Neural Network Models

“…For comprehensive reviews on forecasting the ICT vulnerabilities, we recommend the papers: Roumani et al [5], Yasasin et al [6] and more recently Cosma et al [1], who presented a comparative study of the most important and promising methods for forecasting the ICT systems vulnerabilities.…”

“…This paper presents a comparison of several types of Neural Networks (NN) for forecasting the number of software bugs and vulnerabilities that will be discovered for a software component in certain timeframe, in terms of accuracy, trainability and Technical University of Cluj Napoca, North University Centre of Baia Mare, e-mail: 1 {ovidiu.cosma, petrica.pop, cosmin.sabo}@cunbm.utcluj.ro, 2 laura.ov.cosma@student.utcluj.ro stability to configuration parameters. The experimental part of this paper covers the Ubuntu Operating System and the Robot Operating System (ROS) which represents a set of software libraries and tools needed to build a robot application.…”