Evaluación de algoritmos de minería de datos para detección y predicción de Ataques de Inyección SQL en Big Data : Evaluación de un Perceptrón Multicapa para la detección y predicción de Ataques de Inyección SQL en Big Data.

Abstract

SQL Injection Attacks (SQLIA) are currently in third place on the OWASP (Open Web Application Security Project) TOP 10 list: 2021, mainly due to their easy exploitability. However, the execution of these attacks is detrimental to current computer systems. Due to their complexity, it is not possible to take the necessary measures to mitigate these attacks' threats is impossible. This component systematically investigates the literature related to algorithms and data mining techniques to detect and prevent SQLIAs. Based on this research, a data mining algorithm is evaluated to determine the degree of effectiveness when detecting text strings that could result in a possible SQLIA. Subsequently, a prototype system is developed that allows monitoring log records and data entries using the evaluated algorithm to detect and prevent SQLIAs. This component aims to increase the confidence and security of the organization's systems where the developed system is implemented.