SoK: How Frontier AI Reshapes System-Level Security Risk Dynamics in Critical Infrastructure
Chandra Thapa, Mohan Baruwal Chhetri, Marthie Grobler, Shahroz Tariq, Tooba Aamir
cs.CR
Submitted: 2026-08-03
Comments: 19 pages
License: http://creativecommons.org/licenses/by-sa/4.0/
The gist: Frontier artificial intelligence (FAI), encompassing large-scale, general-purpose AI systems, including large language models, multimodal foundation models, and agentic systems, is increasingly
Terminology
Abstract
Frontier artificial intelligence (FAI), encompassing large-scale, general-purpose AI systems, including large language models, multimodal foundation models, and agentic systems, is increasingly integrated into critical infrastructure (CI). This challenges long-standing security assumptions of bounded behavior, segmented networks, component transparency, and human-paced decision-making. Existing AI-security literature typically organizes risks by attack type, lifecycle stage, or asset class, but fails to capture the system-level dynamics, such as how risk emerges, spreads, and is controlled, through which FAI reshapes CI security outcomes. This Systematization of Knowledge (SoK) introduces a five-dimensional risk-dynamics framework that characterizes how FAI reconfigures CI security across the lifecycle: (i) Capability Emergence through new FAI-enabled attack and defense capabilities, (ii) Infiltration Pathways through data, models and AI supply chains, (iii) Cross-System Propagation across interconnected infrastructures and dependencies, (iv) degradation of effective technical and human Control Authority, and (v) strain on institutional Response Capacity under operational pressure. Rather than enumerating threats, the framework identifies recurring mechanisms that jointly determine system-level risk. We further identify a structural mismatch between academic AI-security research and CI operational constraints, and derive a deployment-oriented research agenda grounded in system-level assurance criteria. Collectively, this work shifts attention from model-centric robustness to lifecycle-structured, system-level assurance in interconnected CI environments.
Sources
- Alignment, Agency and Autonomy in Frontier AI: A Systems Engineering Perspective
- From Transformers to Large Language Models: A systematic review of AI applications in the energy sector towards Agentic Digital Twins
- TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems
- Agentic AI for autonomous anomaly management in complex systems
- Standardized Threat Taxonomy for AI Security, Governance, and Regulatory Compliance
- Military AI Cyber Agents (MAICAs) Constitute a Global Threat to Critical Infrastructure
- A Framework for Evaluating Emerging Cyberattack Capabilities of AI
- Frontier AI's Impact on the Cybersecurity Landscape
- Agentic AI Frameworks: Architectures, Protocols, and Design Challenges
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills