Toward a Dynamic Stackelberg Game-Theoretic Framework for Agentic AI Defense Against LLM Jailbreaking

Researchers propose a game-theoretic framework using Stackelberg equilibrium and Rapidly exploring Random Trees to model interactions between attackers trying to jailbreak LLMs and defensive AI systems. The framework provides a mathematical foundation for understanding and improving AI safety guardrails against prompt-based attacks.

• →New game-theoretic model treats LLM jailbreaking as a strategic interaction between attackers and defenders using extensive form games.
• →Framework combines Rapidly exploring Random Trees search with Stackelberg equilibrium to capture both attack discovery and defensive responses.
• →The model explains when attackers can no longer find profitable prompt deviations through local equilibrium conditions.
• →Research introduces 'Purple Agent defense' as a theoretical approach to hardening LLM guardrails.
• →Framework offers principled mathematical foundation for evaluating and improving AI safety measures.