DESIGN AND IMPLEMENTATION OF INJECTION ATTACK DETECTION ON WEB APPLICATION USING NAÏVE BAYESSIAN ALGORITHM

Injection attacks are one type of attack that always happened to get vulnerability in web applications. There are several types of injection attacks, that are sql injection and cross-site scripting (XSS). According to statistics released by Imperva in 2018, there has been an increase of 267% of inje...

Full description

Saved in:
Bibliographic Details
Main Author: Akbar Anggamaulana, Mochamad
Format: Theses
Language:Indonesia
Online Access:https://digilib.itb.ac.id/gdl/view/39043
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Institut Teknologi Bandung
Language: Indonesia
id id-itb.:39043
spelling id-itb.:390432019-06-21T13:08:57ZDESIGN AND IMPLEMENTATION OF INJECTION ATTACK DETECTION ON WEB APPLICATION USING NAÏVE BAYESSIAN ALGORITHM Akbar Anggamaulana, Mochamad Indonesia Theses Web application, Detection, Machine learning, Injection attack, Naïve bayes INSTITUT TEKNOLOGI BANDUNG https://digilib.itb.ac.id/gdl/view/39043 Injection attacks are one type of attack that always happened to get vulnerability in web applications. There are several types of injection attacks, that are sql injection and cross-site scripting (XSS). According to statistics released by Imperva in 2018, there has been an increase of 267% of injection attacks compared to 2017. There are various ways that can be done to detect injection attacks on the web application. Some ways that can be done to detect are with whitebox test and blackbox test. In this study, the authors purposed to design a system that can be detected a vulnerability of security on web applications with blackbox using machine learning and the Bayes naive classification as algorithm. The dataset that is made by manually with the specified of specifications. Based on these results from the level of precision, recall and accuracy of the proposed system is quite good. text
institution Institut Teknologi Bandung
building Institut Teknologi Bandung Library
continent Asia
country Indonesia
Indonesia
content_provider Institut Teknologi Bandung
collection Digital ITB
language Indonesia
description Injection attacks are one type of attack that always happened to get vulnerability in web applications. There are several types of injection attacks, that are sql injection and cross-site scripting (XSS). According to statistics released by Imperva in 2018, there has been an increase of 267% of injection attacks compared to 2017. There are various ways that can be done to detect injection attacks on the web application. Some ways that can be done to detect are with whitebox test and blackbox test. In this study, the authors purposed to design a system that can be detected a vulnerability of security on web applications with blackbox using machine learning and the Bayes naive classification as algorithm. The dataset that is made by manually with the specified of specifications. Based on these results from the level of precision, recall and accuracy of the proposed system is quite good.
format Theses
author Akbar Anggamaulana, Mochamad
spellingShingle Akbar Anggamaulana, Mochamad
DESIGN AND IMPLEMENTATION OF INJECTION ATTACK DETECTION ON WEB APPLICATION USING NAÏVE BAYESSIAN ALGORITHM
author_facet Akbar Anggamaulana, Mochamad
author_sort Akbar Anggamaulana, Mochamad
title DESIGN AND IMPLEMENTATION OF INJECTION ATTACK DETECTION ON WEB APPLICATION USING NAÏVE BAYESSIAN ALGORITHM
title_short DESIGN AND IMPLEMENTATION OF INJECTION ATTACK DETECTION ON WEB APPLICATION USING NAÏVE BAYESSIAN ALGORITHM
title_full DESIGN AND IMPLEMENTATION OF INJECTION ATTACK DETECTION ON WEB APPLICATION USING NAÏVE BAYESSIAN ALGORITHM
title_fullStr DESIGN AND IMPLEMENTATION OF INJECTION ATTACK DETECTION ON WEB APPLICATION USING NAÏVE BAYESSIAN ALGORITHM
title_full_unstemmed DESIGN AND IMPLEMENTATION OF INJECTION ATTACK DETECTION ON WEB APPLICATION USING NAÏVE BAYESSIAN ALGORITHM
title_sort design and implementation of injection attack detection on web application using naãve bayessian algorithm
url https://digilib.itb.ac.id/gdl/view/39043
_version_ 1822925178077708288