paperAugust 2026Unreviewed

SoK: How Frontier AI Reshapes System-Level Security Risk Dynamics in Critical Infrastructure

C. Thapa, Mohan Baruwal Chhetri, M. Grobler, Shahroz Tariq, Tooba Aamir

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

Cite

@misc{thapa2026sok,
  title = {{SoK: How Frontier AI Reshapes System-Level Security Risk Dynamics in Critical Infrastructure}},
  author = {C. Thapa and Mohan Baruwal Chhetri and M. Grobler and Shahroz Tariq and Tooba Aamir},
  year = {2026},
  month = aug,
  eprint = {2608.04033},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/93c0882ee73a87235659637c1d1d59d0c14e83cd}
}