Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/89547
Title: | Detección de malware, métodos estadísticos y machine learning |
Author: | Ruiz Ruiz, Javier |
Tutor: | Elbaz Sanz, Angel |
Abstract: | In a partially digitized world and where most everyday actions are influenced by computer systems, it is necessary to know the risks that computer attacks and the distribution of malicious software or malware can suppose. This type of software, normally distributed by large groups or associations of criminals, tries to obtain the economic benefit from the damages that it can produce in the target. It is a persistent and day-to-day threat that affects both, users and companies around the world. It is important to know the presence of these activities and be able to carry out a study and analysis of them. The analyses that are perfromed on this type of software are commonly dedicated to know if the software is really bad intentional or if instead it is a legitimate software. Currently, these classifications and detections are made based on "signatures" or rules present in antivirus systems trying to recognize the characteristic patterns of threats. The problem with this type of detections is the short scalability that can be seen when a sample is modified enough for these signatures in order to make them unable to recognize, making the continous study of malware samples necessary by analysts. Therefore, this document tries to propose a solution that facilitates the recognition of malicious software and reduces manual work, as well as the scalability of the system using machine learning techniques. |
Keywords: | machine learning malware computer security |
Document type: | info:eu-repo/semantics/masterThesis |
Issue Date: | Dec-2018 |
Publication license: | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
Appears in Collections: | Trabajos finales de carrera, trabajos de investigación, etc. |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
jaruizrTFM0119memoria.pdf | Memoria del TFM | 2,71 MB | Adobe PDF | View/Open |
Share:
This item is licensed under a Creative Commons License