Cyber-attack detection on maritime autonomous surfaceships: python based predictive analysis

Abstract

Maritime Autonomous Surface Ships (MASS) that are used for navigation, cargo handling and communication on a digital system. It improves operational efficiency and maximizes cyber risk threats. This project is based on the framework that incorporates cybersecurity methodology and examines dynamic data such as geo-location coordinates, timestamp, navigation map status, performance, efficiency, cargo type, data source and destination port that are grounded in the operating unit. By understanding these analytics based on Python, machine learning (ML) and deep learning techniques that use the system to easily analyze both real-time and Automatic Identification System (AIS) datasets that helps to detect any anomalies present in the patterns that are linked to potential cyber threats. Anomalies are detected in an early phase and the model supports the risk mitigation and strengthens the autonomous maritime operations. Informed decision making can support proactive monitoring of maritime which is supported by AIS data feature which also improve accuracy and reliability. This paper aim is to propose the model which is more reliable, expandable, and accurate prediction through the use of hybrid model which also incorporates the concept of long short-term memory (LSTM) and random forest which is also helpful in further classification and extraction. The model aims to enhance the detection accuracy with techniques such as deep learning and ML.