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

arXiv: https://arxiv.org/abs/2604.23341 · HTML: https://mlsanity.com/paper/2604.23341/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 25 Apr 2026.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 9 of 9)

- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs](https://mlsanity.com/paper/2404.08555/) (2024)
- [Towards Explainable Network Intrusion Detection using Large Language Models](https://mlsanity.com/paper/2408.04342/) (2024)
- [ChatGPT and Other Large Language Models for Cybersecurity of Smart Grid Applications](https://mlsanity.com/paper/2311.05462/) (2023)
- [PowerGraph-LLM: Novel Power Grid Graph Embedding and Optimization with Large Language Models](https://mlsanity.com/paper/2501.07639/) (2025)
- [BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage](https://mlsanity.com/paper/2506.02479/) (2025)
- [Large Language Model-Based Framework for Explainable Cyberattack Detection in Automatic Generation Control Systems](https://mlsanity.com/paper/2507.22239/) (2025)
- [Large Language Models for Detecting Cyberattacks on Smart Grid Protective Relays](https://mlsanity.com/paper/2601.04443/) (2026)

## Abstract (arXiv)

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 LLMs (OpenAI's GPT-4o mini, Google's Gemini 2.0 Flash-Lite, and Anthropic's Claude 3.5 Haiku) were tested against Baseline, BitBypass, and DeepInception jailbreaking methods across scenarios derived from nine NERC Reliability Standards (EOP, TOP, and CIP). In the initial broad experiment, the overall Attack Success Rate (ASR) was 33.1%, with DeepInception proving most effective at 63.17% ASR. Claude 3.5 Haiku exhibited complete resistance (0% ASR), while Gemini 2.0 Flash-Lite was most vulnerable (55.04% ASR) and GPT-4o mini moderately susceptible (44.34% ASR). A follow-up experiment refining malicious wording in Baseline and BitBypass attacks yielded a 30.6% ASR, confirming that subtle prompt adjustments can enhance simpler methods' efficacy.