Skjellum, Anthony; Tanis, Craig
College of Engineering and Computer Science
University of Tennessee at Chattanooga
Place of Publication
Over 90% of all goods in the world, at some point in their life, are on a vessel at sea. Currently, the maritime industry relies on the Automatic Identification System (AIS) for collision avoidance and vessel tracking. AIS is an unencrypted, unauthenticated protocol that is vulnerable to various types of cyber attacks allowing malicious actors to alter the location of vessels. With the advent of the Ocean of Things (OoT), vessels are sharing more information than vessel location alone at sea. Increasingly, more information is becoming critical for safe and efficient operation at sea. This method is a novel approach of applying machine learning to build vessel behavior models that exploits such information. These models will allow vessels to detect anomalous communication from vessels nearby. This will enable vessels to determine the quality of the message shared between each other and, more critically, identify malicious actors.
I would like to thank my supervisor, Dr. Farah Kandah, for his guidance through each stage of the process. I want to thank Dr. Anthony Skjellum and Dr. Craig Tanis, for being on my thesis committee and providing helpful feedback. Second, I would especially like to thank my wife, Leora, for her support and countless sacrifices to help me get to this point. To my parents, Dale and Bonnie Coleman, and my brother and sister in law, Joshua and Amanda, for their continued support and encouragement.
M. S.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Science.
Anomaly detection (Computer security); Machine learning; Ships -- Automatic identification systems
xiv, 75 leaves.
Coleman, Jacob, "Behavioral Model Anomaly Detection in Automatic Identification Systems (AIS)" (2020). Masters Theses and Doctoral Dissertations.