Agentic AI for Cyber Resilience: A New Security Paradigm and Its System-Theoretic Foundations

2025-12-28

AI Summary

Traditional cybersecurity architectures—relying on static rules and perimeter-based defense—are inadequate against large language model (LLM)-driven adaptive attacks. Method: This paper proposes a novel network resilience paradigm centered on autonomous intelligent agents, shifting security from “prevention-first” to “resilience-through-adaptation.” The paradigm mandates four core capabilities under attack: interference prediction, critical function maintenance, rapid recovery, and continuous learning. We integrate systems theory with game theory to formalize an agent-centric design framework that unifies autonomy allocation, information flow modeling, and temporal orchestration. The architecture combines LLM-driven reasoning, automated penetration testing, proactive deception, and closed-loop remediation. Contribution/Results: Experimental evaluation demonstrates significant improvements in adversarial robustness, functional continuity, and recovery efficiency across threat response and cyber-deception scenarios.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Adversarial Agents
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Cybersecurity is being fundamentally reshaped by foundation-model-based artificial intelligence. Large language models now enable autonomous planning, tool orchestration, and strategic adaptation at scale, challenging security architectures built on static rules, perimeter defenses, and human-centered workflows. This chapter argues for a shift from prevention-centric security toward agentic cyber resilience. Rather than seeking perfect protection, resilient systems must anticipate disruption, maintain critical functions under attack, recover efficiently, and learn continuously. We situate this shift within the historical evolution of cybersecurity paradigms, culminating in an AI-augmented paradigm where autonomous agents participate directly in sensing, reasoning, action, and adaptation across cyber and cyber-physical systems. We then develop a system-level framework for designing agentic AI workflows. A general agentic architecture is introduced, and attacker and defender workflows are analyzed as coupled adaptive processes, and game-theoretic formulations are shown to provide a unifying design language for autonomy allocation, information flow, and temporal composition. Case studies in automated penetration testing, remediation, and cyber deception illustrate how equilibrium-based design enables system-level resiliency design.

Problem

• Shifts cybersecurity from prevention to agentic resilience using AI.
• Develops a system-level framework for designing AI-driven security workflows.
• Applies game theory to balance attacker and defender adaptive processes.

Innovation

• Agentic AI enables autonomous planning and adaptation
• System-theoretic framework designs AI workflows for resilience
• Game theory unifies autonomy allocation and information flow