Security Assessment of Software Design using Neural Network

TL;DR

This paper proposes a neural network-based method to assess software security during the design phase, aiming to identify attack patterns early and reduce costs associated with late-stage security fixes.

Contribution

It introduces a novel approach using back propagation neural networks to evaluate security in software design, facilitating early detection of vulnerabilities.

Findings

Neural network successfully identifies attack patterns from design scenarios.

Performance metrics demonstrate effectiveness of the neural network approach.

Early security assessment reduces potential costs of late-stage fixes.

Abstract

Security flaws in software applications today has been attributed mostly to design flaws. With limited budget and time to release software into the market, many developers often consider security as an afterthought. Previous research shows that integrating security into software applications at a later stage of software development lifecycle (SDLC) has been found to be more costly than when it is integrated during the early stages. To assist in the integration of security early in the SDLC stages, a new approach for assessing security during the design phase by neural network is investigated in this paper. Our findings show that by training a back propagation neural network to identify attack patterns, possible attacks can be identified from design scenarios presented to it. The result of performance of the neural network is presented in this paper.