A Game-Theoretic Foundation of Deception: Knowledge Acquisition and Fundamental Limits
This work addresses deception modeling for security and AI systems, but it appears incremental as it builds on existing game theory concepts.
The paper tackles the problem of modeling deception in strategic interactions by proposing a game-theoretic framework to analyze attacks and defenses, characterizing equilibria and conditions for knowledge enhancement.
Deception is a technique to mislead human or computer systems by manipulating beliefs and information. Successful deception is characterized by the information-asymmetric, dynamic, and strategic behaviors of the deceiver and the deceivee. This paper proposes a game-theoretic framework of a deception game to model the strategic behaviors of the deceiver and deceivee and construct strategies for both attacks and defenses over a continuous one-dimensional information space. We use the signaling game model to capture the information-asymmetric, dynamic, and strategic behaviors of deceptions by modeling the deceiver as a privately-informed player called sender and the deceivee as an uninformed player called receiver. We characterize perfect Bayesian Nash equilibrium (PBNE) solution of the game and study the deceivability. We highlight the condition of deceivee's knowledge enhancement through evidences to maintain the equilibrium and analyze the impacts of direct deception costs and players' conflict of interest on the deceivability.