Secure Indoor Positioning System Model Menggunakan Serangan Boundary Attack Berbasis Aplikasi Mobile

Muhammad, Banabil Fawazaim (2024) Secure Indoor Positioning System Model Menggunakan Serangan Boundary Attack Berbasis Aplikasi Mobile. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5027201055-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2026. Download (3MB) | Request a copy

Abstract

Selama dekade terakhir, perangkat seluler telah berevolusi tidak hanya berfungsi sebagai komunikasi jarak jauh, namun juga sebagai perangkat navigasi menggunakan Global Positioning System (GPS). Karena keterbatasan GPS dalam ruangan, dikembangkan IPS (Indoor Positioning System) sebagai pengganti dari GPS pada saat di dalam ruangan. Studi ini menyoroti kurangnya perhatian terhadap keamanan dan privasi dalam pengembangan IPS, terutama dalam menghadapi serangan keamanan seperti serangan Boundary Attack. Penelitian ini bertujuan untuk membuat IPS yang tahan terhadap serangan Boundary Attack dengan mengembangkan model menggunakan data sidik jari Channel State Information (CSI). Tujuan dari penelitian ini mencakup membandingkan kinerja antara model IPS dan model rekan terhadap serangan serangan perimeter, dan mengintegrasikan model dengan aplikasi seluler untuk menampilkan lokasi pengguna secara real time. Metode penelitiannya antara lain mengumpulkan dataset dari Tower 2 ITS, membangun dan melatih model IPS menggunakan data yang diserang dan tidak diserang, menerapkan serangan Boundary Attack, dan membuat aplikasi seluler terintegrasi. Hasil penelitian meliputi evaluasi akurasi model sebelum dan sesudah serangan serta perbandingan dengan model pembanding dalam kondisi serangan. Model IPS berhasil dibangun yang dapat menahan serangan Boundary Attack dan menjaga akurasi bahkan setelah serangan tersebut. Membandingkan model IPS dengan model pembanding menunjukkan ketahanan yang baik terhadap serangan. Dengan mengintegrasikan aplikasi mobile dengan IPS melalui Flask, pengguna dapat melihat lokasinya dengan akurasi tinggi dan real time.
=================================================================================================================================
Over the past decade, mobile devices have evolved to function not only as long-distance communication, but also as navigation devices using the Global Positioning System (GPS). Due to the limitations of indoor GPS, IPS (Indoor Positioning System) was developed as a replacement for GPS when indoors. This study highlights the lack of attention to security and privacy in the development of IPS, especially in the face of security attacks such as Boundary Attack. This research aims to create an IPS that is resistant to Boundary Attack by developing a model using Channel State Information (CSI) fingerprint data. The objectives of this research include comparing the performance between the IPS model and the peer model against perimeter attack attacks, and integrating the model with a mobile application to display the user's location in real time. The research methods included collecting datasets from Tower 2 ITS, building and training the IPS model using attacked and unattacked data, applying the Boundary Attack, and creating an integrated mobile application. The results include an evaluation of the accuracy of the model before and after the attack as well as a comparison with the comparison model under attack conditions. An IPS model was successfully built that can withstand Boundary Attack attacks and maintain accuracy even after such attacks. Comparing the IPS model with the comparison model shows good resistance to attacks. By integrating a mobile application with the IPS through Flask, users can view their location with high accuracy and in real time.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Indoor Positioning System, Machine Learning, Channel State Information
Subjects:	T Technology > T Technology (General) > T11 Technical writing. Scientific Writing T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information Technology > 59201-(S1) Undergraduate Thesis
Depositing User:	Banabil Fawazaim Muhammad
Date Deposited:	05 Feb 2024 06:05
Last Modified:	05 Feb 2024 06:05
URI:	http://repository.its.ac.id/id/eprint/106076

Actions (login required)

View Item