1. Repositório Aberto da Universidade do Porto
2. FEUP - Faculdade de Engenharia
3. FEUP - Dissertação

Author(s):	José Pedro Passos Leocádio
Title:	Protecting IOT devices against cyberattacks using deep learning to classify radio-frequency emissions of code running on the processor
Issue Date:	2021-02-12
Description:	The main goal of this project is to detect anomalous behavior on devices by capturing and analyzing the RF emissions that are produced every time there is code running in their processors. These emissions cannot be manipulated or controlled, which makes them a truly reliable source when it comes to detecting the state of a device. Both Program Counter(PC) and Instruction Register(IR) registers will be used to help characterize the device's behavior, more precisely, it will be used the Hamming Distances(HD) between instructions of these two registers. To achieve this, firstly, it will be necessary to implement multiple behaviors in a device, at least one where the Program Counter is isolated, one where the Instruction Register is isolated, a normal one and a malicious/abnormal one. Then, using an RF probe, all the RF emissions resulting from executing these behaviors will be captured and will be analysed using signal processing and machine learning techniques. At the end, the system should be able to predict the correct HD of PC and IR and classify the state of the device as normal or not.
Subject:	Engenharia electrotécnica, electrónica e informática Electrical engineering, Electronic engineering, Information engineering
Scientific areas:	Ciências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática Engineering and technology::Electrical engineering, Electronic engineering, Information engineering
DOI:	10.34626/1p20-t327
TID identifier:	202827534
URI:	https://hdl.handle.net/10216/133036
Document Type:	Dissertação
Rights:	openAccess
Appears in Collections:	FEUP - Dissertação

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.