Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards

Abstract

The deployment of Large Language Models (LLMs) as assistants in electric grid operations promises to streamline compliance and decision-making but exposes new vulnerabilities to prompt-based adversarial attacks. This paper evaluates the risk of jailbreaking LLMs, i.e., circumventing safety alignments to produce outputs violating regulatory standards, assuming threats from authorized users, such as operators, who craft malicious prompts to elicit non-compliant guidance. Three state-of-the-art LLM

Categories

Framework mappings

Suggested from the entry's categories.

@misc{hammadia2026evaluating,
  title = {{Evaluating Jailbreaking Vulnerabilities in LLMs Deployed as Assistants for Smart Grid Operations: A Benchmark Against NERC Standards}},
  author = {Taha Hammadia and Lucas Rea and Ahmad Mohammad Saber and Amr Youssef and Deepa Kundur},
  year = {2026},
  month = apr,
  eprint = {2604.23341},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.23341}
}