Towards Defining Deception in Structural Causal Games

Abstract

Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals. There are a number of existing definitions of deception in the literature on game theory and symbolic AI, but there is no overarching theory of deception for learning agents in games. We introduce a functional definition of deception in structural causal games, grounded in the philosophical literature. We present several examples to establish that our formal definition captures philosophical and commonsense desiderata for deception.