LLM Semantic Signaling Game and Mechanism Design: Systematic Blindness, Awareness Shaping, and Mindset Dynamics

2026-06-27

AI Summary

This work addresses the vulnerability of large language models to semantic deception in strategic interactions, emphasizing the urgent need to model receivers’ perceptual blind spots and develop robust defense mechanisms. The paper introduces the first formal framework of semantic signaling games, integrating prompt control, statistical detection, and perfect Bayesian Nash equilibrium analysis to shape awareness and regulate collective behavior, thereby steering systems toward benign equilibria. By employing Gaussian approximation and likelihood ratio–based decision rules, the approach effectively quantifies the impact of awareness levels, reveals the dynamics of cognitive evolution, and significantly reduces the success rate of phishing attacks, thereby enhancing the security of human–AI communication.

Abstract

Large language models (LLMs) increasingly mediate strategic interactions through natural language, making semantic control a critical element of communication and deception. This paper develops a semantic signaling game in which a sender selects a semantic control, an LLM generates a stochastic message, and a receiver evaluates the message using an awareness-dependent scoring mechanism. Receiver awareness is modeled as a type that determines which linguistic features are perceived and used for inference, providing a formal model of systematic blindness. The framework connects prompt-based control, statistical detection, and game-theoretic equilibrium analysis. Gaussian approximations of aggregate message scores enable likelihood-ratio decision rules, while Perfect Bayesian Nash equilibria characterize strategic behavior. The paper further develops mechanism-design approaches that reshape receiver awareness, penalize deceptive semantic controls, and modify receiver populations to induce benign pooling equilibria. Numerical experiments validate the Gaussian approximation, quantify awareness-ordering effects, analyze mindset dynamics under adaptive adversaries, and demonstrate how awareness shaping and guardrail costs reduce successful phishing attacks. The proposed framework provides a principled foundation for analyzing strategic language-mediated interactions in agentic AI systems and offers new tools for the design of robust and secure human-AI communication.

Problem

• semantic signaling
• systematic blindness
• awareness shaping
• strategic communication
• deception

Innovation

• semantic signaling game
• awareness shaping
• systematic blindness
• mechanism design
• Perfect Bayesian Nash equilibrium