Underwater drones are vital for scientific research, environmental monitoring, and maritime operations, allowing data collection in challenging environments. However, their deployment faces issues such as low bandwidth, high latency, signal attenuation, and intermittent connectivity due to mobility and water currents. Traditional centralized data processing approaches are inefficient under these conditions as they require transmitting large volumes of raw data to a central location. To address these challenges, this study proposes a Federated Learning (FL) framework specifically tailored for underwater networks. Unlike centralized approaches, FL enables underwater drones to collaboratively train a global intrusion detection model by processing data locally and sharing only model updates with the central server. This approach significantly improves data security by ensuring that sensitive information never leaves the local device, reducing the risk of interception or compromise during transmission. Furthermore, FL’s decentralized architecture inherently aligns with the dynamic and distributed nature of underwater drone networks. The proposed framework improves cyber intrusion detection by leveraging localized insights from individual drones to detect threats, including zero-day attacks, without directly exposing sensitive data. By preserving privacy and enabling collaborative anomaly detection, FL addresses key cybersecurity challenges in the Internet of Underwater Things (IoUT).
This paper presents an extensive analysis of oceanic environmental data collected by Ocean Networks Canada in Discovery Passage over the past five years. Using advanced sensor technology, we collected comprehensive datasets on ocean factors such as temperature, salinity, pH levels, and other critical parameters. Through meticulous data cleaning processes and advanced analytics, including statistical analysis and machine learning models, we systematically examined these large datasets to identify significant trends and patterns in the ocean environment. Our findings reveal notable changes and dynamics in the ecosystem, which are visualized through a series of detailed graphs. These visualizations not only enhance our understanding of the current state of the ocean but also underscore the potential long-term impacts of environmental changes. The insights gained from this study contribute significantly to the field of oceanography by providing a clearer picture of ocean health and laying a foundation for future research on sustainable ocean management and environmental conservation.
The rapid expansion of underwater communication networks through autonomous drones and sensors marks a significant advancement in ocean exploration and data collection. However, this growth introduces new vulnerabilities, particularly to DDoS attacks, jeopardizing the integrity of IoUT (Internet of Underwater Things)devices. Effective mitigation of these attacks requires tailored defence strategies suited to submerged environments. This study provides quality IoUT datasets and presents a predictive model leveraging machine learning techniques to detect and mitigate DDoS threats in underwater networks. By analyzing network traffic, we employ classifiers such as Decision Trees, AdaBoost, SVM, K-Nearest Neighbours, and Random Forests to enhance detection accuracy and response times. The enhanced machine learning result was provided for various conditions of the underwater network (base, light, medium, heavy, and extreme conditions). Compared with prior IoT and IoUT studies, in a terrestrial environment, the accuracy is reported as 99%. The model maintained 99% in base condition and 96% for both validation and test accuracy at 1 meter depth. To validate the models, real-world aquatic environment datasets are collected from various locations and depths. In addition, a data validation model was implemented to verify the quality of the dataset. The proposed solution aims to strengthen the security framework of IoUT devices, ensuring the protection of critical underwater data from emerging cyber threats.