Deceptive Planning Exploiting Inattention Blindness

2025-10-03

AI Summary

This paper investigates “inadvertent inattentional blindness” in two-player zero-sum stochastic games, wherein Player 1—constrained in sensor selection—fails to detect Player 2’s deviation from safety strategies due to biased prior beliefs, enabling systematic exploitation. Method: We propose a value-weighted sensor selection objective function, the first to incorporate “rational inattention” theory into zero-sum stochastic game modeling; develop a formal model of exploitable attention blind spots; and design an online, monotonic, greedy myopic sensor selection mechanism. Contribution/Results: Experiments demonstrate that the perception-constrained player persistently selects sensors aligned with its prior, forming stable blind spots that allow the opponent to consistently exceed its security value. This work establishes a novel paradigm of cognitive-bias-driven strategic deception and provides both theoretical foundations and an algorithmic framework for security and adversarial modeling under perceptual constraints.

Technology Category

• Game Theory and Economic Paradigms: Adversarial Learning
• Reasoning under Uncertainty: Sequential Decision Making
• Search and Optimization: Adversarial Search

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

Abstract

We study decision-making with rational inattention in settings where agents have perception constraints. In such settings, inaccurate prior beliefs or models of others may lead to inattention blindness, where an agent is unaware of its incorrect beliefs. We model this phenomenon in two-player zero-sum stochastic games, where Player 1 has perception constraints and Player 2 deceptively deviates from its security policy presumed by Player 1 to gain an advantage. We formulate the perception constraints as an online sensor selection problem, develop a value-weighted objective function for sensor selection capturing rational inattention, and propose the greedy algorithm for selection under this monotone objective function. When Player 2 does not deviate from the presumed policy, this objective function provides an upper bound on the expected value loss compared to the security value where Player 1 has perfect information of the state. We then propose a myopic decision-making algorithm for Player 2 to exploit Player 1's beliefs by deviating from the presumed policy and, thereby, improve upon the security value. Numerical examples illustrate how Player 1 persistently chooses sensors that are consistent with its priors, allowing Player 2 to systematically exploit its inattention.

Problem

• Modeling deceptive planning exploiting rational inattention blindness
• Formulating perception constraints as online sensor selection problems
• Developing algorithms for exploiting incorrect beliefs in zero-sum games

Innovation

• Online sensor selection with value-weighted objective function
• Greedy algorithm for monotone objective function optimization
• Myopic decision-making algorithm exploiting opponent's belief deviations