skip to main content

AOE Home / About / AOE seminars / Archive / 2016 

Detection and Mitigation of Cyber-Physical Attacks in Autonomous Systems Using Game Theory and Learning

March 23, 2016

  • Dr. Kyriakos Vamvoudakis
  • University of California Santa Barbara
  • Torg 1060
  • 4:00 p.m.
  • Faculty Host: Dr. Farhood

Abstract: Embedded sensors, computation, and communication have enabled the development of sophisticated sensing devices for a wide range of cyber-physical applications that include safety monitoring, surveillance, motion planning, search and rescue, traffic monitoring, and power systems. However, the deployment of such devices has been slowed by concerns regarding their vulnerability to both stochastic failures and cyber-physical attacks. Nowadays the efficiency will be defined by our potentials to adapt (complete autonomy) in decentralized, unknown and complex environments to enable capabilities beyond human limits. Until the achievement of near-complete autonomy, sensor technologies remain a critical issue for Unmanned Aerial Vehicle (UAV) control systems. In the first part of the talk, I will address the problem of estimating the true status of an event based on a multitude of sensors that may have been tempered by an attacker, i.e. the estimation of a binary random variable based on noisy and attacked measurements. The estimation problem is formulated as a zero-sum partial information game in which a detector attempts to minimize the probability of an estimation error and an attacker attempts to maximize this probability. A significant novelty of our approach with respect to classic problems of Byzantine faults is that we do not assume perfect sensors, i.e., even the sensors that have not been manipulated can produce incorrect results, which is common in the network-security domain. In the second part of the talk, I will use techniques from approximate dynamic programming and learning to design a new family of model-free plug-n-play autonomous control algorithms to mitigate cyber-physical attacks and faults. These algorithms will converge online, in real time to game-theoretic solutions even when attacked by persistent adversaries including jammers. Finally, I will show some experimental results of a UAV (a cyber physical system that includes an avionic system and several sensor systems) under cyber-physical attacks. The proposed approaches combine networked feedback control, game theory, network security, reinforcement learning, and serve as a tool for approaching difficult problems that without learning-based approaches are hard or impossible to solve.

Bio Kyriakos G. Vamvoudakis received the Diploma (a 5 year degree, equivalent to a Master of Science) in Electronic and Computer Engineering from Technical University of Crete, Greece in 2006 with highest honors. After moving to the United States of America, he studied at The University of Texas with Frank L. Lewis as his advisor and he received his M.S. and Ph.D. in Electrical Engineering in 2008 and 2011 respectively. From May 2011 to January 2012, he was working as an Adjunct Professor and Faculty Research Associate at the University of Texas and at the Automation and Robotics Research Institute. He currently serves as a Project Research Scientist and Faculty Lecturer at the Center for Control, Dynamical systems and Computation (CCDC) at the University of California, Santa Barbara. His research interests include networked control, network security, fault-tolerant control, multi-agent optimization, optimal adaptive control, reinforcement learning and game theory. He is coauthor of one patent, 14 book chapters, more than 90 technical publications, and 2 books; Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles (IET) and Complex Systems: Theory and Applications (Elsevier). Dr. Vamvoudakis is the recipient of several international awards including the 2016 International Neural Network Society Young Investigator (INNS) Award, the Best Paper Award for Autonomous/Unmanned Vehicles at the 27th Army Science Conference in 2010, the Best Presentation Award at the World Congress of Computational Intelligence in 2010, and the Best Researcher Award from the Automation and Robotics Research Institute in 2011. He is a member of Tau Beta Pi, Eta Kappa Nu and Golden Key honor societies and is listed in Who's Who in the World, Who's Who in Science and Engineering, and Who's Who in America. He currently is a member of the Technical Committee on Intelligent Control of the IEEE Control Systems Society (TCIC), a member of the Technical Committee on Adaptive Dynamic Programming and Reinforcement Learning of the IEEE Computational Intelligence Society (ADPRLTC), an Associate Editor of the Journal of Optimization Theory and Applications (JOTA), an Associate Editor on the IEEE Control Systems Society Conference Editorial Board, an Editor in Chief of the Communications in Control Science and Engineering, a registered Electrical/Computer engineer (PE) and a member of the Technical Chamber of Greece. He is a Senior Member of IEEE.

Tags

    Tags