Desarrollo de una red neuronal MLP para la detección de Botnets en el conjunto de datos UNSW BOT-IOT
This project deals with the development of an MLP neural network that detects malicious attacks within the network; introducing neural networks and presenting the characteristics and models used to theoretically explain the detection of botnets in the UNSW-BoT-IoT data set. The data set called UNSW-...
Guardat en:
| Autor principal: | |
|---|---|
| Format: | bachelorThesis |
| Idioma: | spa |
| Publicat: |
2020
|
| Matèries: | |
| Accés en línia: | http://dspace.udla.edu.ec/handle/33000/13096 |
| Etiquetes: |
Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|
Afegir etiqueta | Sumari: | This project deals with the development of an MLP neural network that detects malicious attacks within the network; introducing neural networks and presenting the characteristics and models used to theoretically explain the detection of botnets in the UNSW-BoT-IoT data set. The data set called UNSW-BoT-IoT was taken, which contains botnet attacks including DDos, Dos, the data was analyzed, later the BoT attacks were used to process them with the help of the Pycharm application and its tools Pandas, NumPy and sklearn, which are tools for processing data. Once the data had been processed, the construction of the neural network was carried out by means of the multilayer perceptron model (MLP). The processed data was inserted, and this network was trained, which uses backward propagation or also called delta so that it can identify botnet attacks and thus learn by itself and continue to detect subsequent botnet attacks. |
|---|