Journal
SENSORS
Volume 22, Issue 9, Pages -Publisher
MDPI
DOI: 10.3390/s22093367
Keywords
class balancing; DDoS attacks; deep learning; DoS attacks; intrusion detection system; IoT networks; machine learning
Funding
- FRIDA (Fondo Regional para la Innovacion Digital en America Latina y el Caribe)
- project Red tematica Ciencia y Tecnologia para el Desarrollo (CYTED) [519RT0580]
- Ibero-American Science and Technology Program for Development CYTED
Ask authors/readers for more resources
From smart homes to industrial environments, the IoT has become an essential part of our daily lives. However, the increasing number of connected devices also raises concerns about security. This study addresses this issue by building a novel Intrusion Detection System based on Machine Learning and Deep Learning models, achieving high accuracy in identifying denial of service attacks on IoT networks.
From smart homes to industrial environments, the IoT is an ally to easing daily activities, where some of them are critical. More and more devices are connected to and through the Internet, which, given the large amount of different manufacturers, may lead to a lack of security standards. Denial of service attacks (DDoS, DoS) represent the most common and critical attack against and from these networks, and in the third quarter of 2021, there was an increase of 31% (compared to the same period of 2020) in the total number of advanced DDoS targeted attacks. This work uses the Bot-IoT dataset, addressing its class imbalance problem, to build a novel Intrusion Detection System based on Machine Learning and Deep Learning models. In order to evaluate how the records timestamps affect the predictions, we used three different feature sets for binary and multiclass classifications; this helped us avoid feature dependencies, as produced by the Argus flow data generator, whilst achieving an average accuracy >99%. Then, we conducted comprehensive experimentation, including time performance evaluation, matching and exceeding the results of the current state-of-the-art for identifying denial of service attacks, where the Decision Tree and Multi-layer Perceptron models were the best performing methods to identify DDoS and DoS attacks over IoT networks.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available