UNITesi

The thesis investigates a lightweight intrusion detection system for IoT network traffic using the CICIoT2023 dataset and neural models based on CNN and CNN/LSTM architectures. The comparative results identify a promising cloud-assisted edge solution in which a more complex teacher model guides the training of a compact student model, considered as a candidate for future local deployment on an edge gateway.

The thesis investigates a lightweight intrusion detection system for IoT network traffic using the CICIoT2023 dataset and neural models based on CNN and CNN/LSTM architectures. The comparative results identify a promising cloud-assisted edge solution in which a more complex teacher model guides the training of a compact student model, considered as a candidate for future local deployment on an edge gateway.

THREAT DETECTION IN THE INTERNET OF THINGS: A HYBRID DEEP LEARNING ARCHITECTURE FOR LARGE-SCALE NETWORK TRAFFIC ANALYSIS

PASTORE, NICOLA
2025/2026

Abstract

The thesis investigates a lightweight intrusion detection system for IoT network traffic using the CICIoT2023 dataset and neural models based on CNN and CNN/LSTM architectures. The comparative results identify a promising cloud-assisted edge solution in which a more complex teacher model guides the training of a compact student model, considered as a candidate for future local deployment on an edge gateway.
2025
THREAT DETECTION IN THE INTERNET OF THINGS: A HYBRID DEEP LEARNING ARCHITECTURE FOR LARGE-SCALE NETWORK TRAFFIC ANALYSIS
The thesis investigates a lightweight intrusion detection system for IoT network traffic using the CICIoT2023 dataset and neural models based on CNN and CNN/LSTM architectures. The comparative results identify a promising cloud-assisted edge solution in which a more complex teacher model guides the training of a compact student model, considered as a candidate for future local deployment on an edge gateway.
IoT
Deep Learning
PIRO, GIUSEPPE
Lauree magistrali a ciclo unico
File in questo prodotto:
Fulltext non presente su UNITESI – Verifica la disponibilità della tesi in formato cartaceo interrogando il Catalogo di Ateneo

I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14253/109566