Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/126948
Title: Analysis of reinforcement learning techniques applied to honeypot systems
Author: Navarro Ferrer, Oriol
Tutor: Torregrosa Garcia, Blas
Others: Prados Carrasco, Ferran  
Abstract: The study of cybersecurity threats is an increasingly relevant element for public and private organizations, due to the increasing number of cyber attacks and their impact on the organizations assets and their reputation. Collecting detailed information that allows to determine how future attacks will be is key to anticipate the organizations' defenses. Tactics, techniques and procedures used by threat actors can be collected using several approaches, one being honeypot systems. The effectiveness of these attack information collection targets depend significantly on their ability to present a realistic environment that can lure attackers to reveal their techniques. This project presents a study of designs and implementations of adaptive honeypots, focused on the use of reinforcement learning, to reach more realistic interactions between honeypots and attackers, and an analysis of the existing techniques and performance metrics.
Keywords: reinforcement learning
honeypot systems
self-adaptive honeypot
threat intelligence
reward functions
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 3-Jan-2021
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 SizeFormat 
onavarrofeTFM021memory.pdfMemory of TFM1,35 MBAdobe PDFThumbnail
View/Open