Overview

The MURI research team will develop a novel game theory framework to address the continuous computer hacking attacks, known as advanced persistent threats, which are essentially a game played between the system and adversary, where each is constantly trying to outsmart the other. A unique trait of advanced persistent threats is that they consist of a variety of different attacks over time. Economic game theory, which most modeling methods are grounded in, does not work well in this type of attack. To develop the new framework, the researchers will use a combination of statistical modeling, adaptive game theory, machine learning and control and systems theory. They plan to model the strategic interactions between the malware attacks and develop a methodology to determine which side is “gaining” or “losing” in the attack, which will enable the system to know when to activate a specific defense.

MURI-image — Schematic of our proposed framework. Click the image to learn more.

Universities

University of Washington

UC Berkeley

University of Illinois Urbana-Champaign

UC Santa Barbara

Georgia Tech

Sponsor

Recent Publications

2022

M.O. Sayin and T. Başar, "Bayesian persuasion with state-dependent quadratic cost measures," IEEE Transactions on Automatic Control (TAC), March 2022.

2021

F. Lane, D. Fridovich-Kiel, C -Y. Chiu, and S. Sastry, "Multi-Hypothesis Interactions in Game-Theoretic Motion Planning." In Proc. of the International Conference on Robotics and Automation (ICRA), 2021. Link: https://arxiv.org/pdf/2011.06047.pdf.
F. Lane, D. Fridovich-Kiel, C -Y. Chiu, and S. Sastry, "Encoding Defensive Driving as a Dynamic Nash Game." In Proc. of the International Conference on Robotics and Automation (ICRA), 2021. Link: https://arxiv.org/pdf/2011.04815.pdf.
C. Maheshwari, C.-Y. Chiu, S. Sastry, and L. Ratliff, "Zeroth-Order Methods for Convex-Concave Minimax Problems: Applications to Decision-Dependent Risk Minimization." 2021. Link: https://arxiv.org/pdf/2106.09082.pdf.
F. Lane, D. Fridovich-Kiel, C -Y. Chiu, and C. Tomlin, "The Computation of Approximate Generalized Feedback Nash Equilibria." 2021. Link: https://arxiv.org/pdf/2101.02900.pdf.
G. Yang, R. Poovendran, and J. Hespanha, "Adaptive learning in two-player Stackelberg games with application to network security," Pre-print available at: https://arxiv.org/abs/2101.03253.
J. Hespanha, "Sensor Manipulation Games in Cyber Security. In Game Theory and Machine Learning for Cyber Security," Charles A. Kamhoua, Christopher D. Kiekintveld, Fei Fang, Quanyan Zhu (ed.), 2021. Link: https://web.ece.ucsb.edu/~hespanha/published/security-sensor-manipulation-chapter.pdf
G. Yang, J. Hespanha, "Modeling and mitigating link-flooding distributed denial-of-service attacks via learning in Stackelberg games," In Handbook of Reinforcement Learning, Vamvoudakis, Kyriakos G., Wan, Yan, Lewis, Frank L., Cansever, Derya (ed.). 2021.https://web.ece.ucsb.edu/~hespanha/published/YH-StbgAdptCtrlNet-BookChapter.pdf
M.O. Sayin and T. Başar, "Pursuasion-based robust sensor design against attackers with unknown control objectives," IEEE Transactions on Automatic Control (TAC), October 2021.
W. Mao, K. Zhang, R. Zhu, D. Simchi-Levi, and T. Başar, "Near-optimal model-free reinforcement learning in non-stationary episodic MDPs, " Proc. International Conference on Machine Learning (ICML); July 2021. Link: https://arxiv.org/pdf/2010.03161.pdf
G. Yang, D. Liberzon, and J. Hespanha, "Topological entropy of switched non-linear systems, " in 24th ACM International Conference on Hybrid Systems: Computation and Control, April 2021. Link: https://dl.acm.org/doi/pdf/10.1145/3447928.3456642
S. Lu, K. Zhang, T. Chen, T. Başar, and L. Horesh, "Decentralized policy gradient descent ascent for safe multi-agent reinforcement learning, " in Proc. AAAI Conference on Artificial Intelligence, February 2021. Link: https://ojs.aaai.org/index.php/AAAI/article/view/17062

More Publications

ONR

MURI PROJECT:

ADAPT

Overview

Universities

Recent Publications

2022

2021