Summaries - Office of Research & Innovation
Research Summaries
Back Application of Generative Adversarial Networks to Predicting and Manipulating Adversary's Behaviors for Mobile Networked Control Systems
Fiscal Year | 2023 |
Division | Research & Sponsored Programs |
Department | Naval Research Program |
Investigator(s) |
Huang, Jefferson
Yoshida, Ruriko |
Sponsor | NPS Naval Research Program (Navy) |
Summary | The increasing use of autonomous systems to improve the operational capabilities of forces on the ground or on manned platforms can potentially present security risks to the supported forces. Specifically, if the autonomous systems are visible to an adversary, their movements can potentially be used by the adversary to predict the operational intent of the supported forces. This was demonstrated in recent work by researchers at the Naval Postgraduate School, who used data from the 2017 Multi-Thread Experiment on San Clemente Island to design a machine learning method for inferring ground force movements based on observing where the supporting autonomous systems are. The focus of this project is on how such autonomous systems can be used in a way that prevents the supported forces' operational intent from being revealed, while still fulfilling the supported forces' needs. |
Keywords | Reinforcement, learning, adversary, response, tracking, prediction |
Publications | Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal |
Data | Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal |