The increasing adoption of Internet of Things (IoT) devices in smart cities and smart farms has led to an upsurge in security threats. These threats not only compromise the integrity of the data but also pose a serious risk to the safety of the environment and human lives. To tackle this issue, the use of intrusion detection systems (IDSs) has gained significant attention.
In this project, we focused on developing a Machine learning-based IDS for smart cities and smart farms. The project involved an extensive literature review of various research papers in the domain. We also carried out simulations in Contiki, NetSim, and Real Hardware to obtain a good and balanced dataset.
To develop an efficient IDS, we pre-processed and encoded data in multiple datasets and applied machine learning techniques to determine if there is an attack or not. In particular, we applied Neural networks to achieve our goal. By leveraging machine learning algorithms, we aimed to achieve high accuracy and low false alarm rates in detecting intrusions in IoT networks.
Overall, our research aimed to contribute to the development of effective IDSs for smart cities and smart farms, enabling the secure deployment and usage of IoT devices in these domains.
This work is partially funded by FCT - Fundação para a Ciência e a Tecnologia, I.P., through the project UIDB/04524/2020.