Enhancing Underwater Network Security: ML-Based Detection and Prediction of DDoS Attacks in IoUT Networks

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.