
handle: 11441/125097
El Internet de las Cosas (IoT) es ya una realidad y su importancia no dejará de crecer en los próximos años. Cualquier “cosa” es susceptible de ser conectada a través de Internet (sensores, cámaras, dispositivos personales, etc) y sus campos de aplicación son también muy diversos: desde la agricultura o la automatización del hogar, hasta la comunicación entre vehículos o el monitoreo remoto de pacientes. A medida que la información intercambiada en estas redes IoT vaya adquiriendo un mayor valor y relevancia, serán fruto de ataques cada vez más diversos y complejos. El objetivo de este trabajo es ver cómo la Inteligencia Artificial, más concretamente el Deep Learning, puede ser aplicado para resolver estos problemas. Se estudiará e implementará una arquitectura de red neuronal de gran importancia dentro de este campo, denominada Autoencoder Variacional Condicional (CVAE), con el fin de realizar una clasificación de diferentes tipos de ataques. Además, se comparará el rendimiento de dicho modelo con otros ya clásicos del Machine Learning, mostrando las diferentes ventajas que ofrece.
The Internet of Things (IoT) is already a reality and its importance will not stop growing in the next years. Any “thing” is susceptible to be connected through Internet (sensors, cameras, personal devices, etc) and its application fields are also very diverse: from the agriculture or home automation, to communication between vehicles or remote patient monitoring. As the exchanged information in these IoT networks gain a greater value and relevance, they will be target of more diverse and complex attacks. The aim of this work is to see how the Artificial Intelligence, more specifically the Deep Learning, can be applied to solve these troubles. A neural network architecture of great importance within of this field will be studied and implemented, called Conditional Variational Autoencoder (CVAE), with the purpose to realize a classification of different types of attacks. Furthermore, the performance of this model will be compared with others Machine Learning classics, showing the different advantages that it offers.
Universidad de Sevilla. Máster en Ingeniería de Telecomunicación
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
