Saved in:
Bibliographic Details
Main Authors: Li, Jiangnan, Yang, Yingyuan, Sun, Jinyuan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.06237
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917991132692480
author Li, Jiangnan
Yang, Yingyuan
Sun, Jinyuan
author_facet Li, Jiangnan
Yang, Yingyuan
Sun, Jinyuan
contents Large language models (LLMs) represent significant breakthroughs in artificial intelligence and hold potential for applications within smart grids. However, as demonstrated in previous literature, AI technologies are susceptible to various types of attacks. It is crucial to investigate and evaluate the risks associated with LLMs before deploying them in critical infrastructure like smart grids. In this paper, we systematically evaluated the risks of LLMs and identified two major types of attacks relevant to potential smart grid LLM applications, presenting the corresponding threat models. We validated these attacks using popular LLMs and real smart grid data. Our validation demonstrates that attackers are capable of injecting bad data and retrieving domain knowledge from LLMs employed in different smart grid applications.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06237
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Risks of Practicing Large Language Models in Smart Grid: Threat Modeling and Validation
Li, Jiangnan
Yang, Yingyuan
Sun, Jinyuan
Cryptography and Security
Large language models (LLMs) represent significant breakthroughs in artificial intelligence and hold potential for applications within smart grids. However, as demonstrated in previous literature, AI technologies are susceptible to various types of attacks. It is crucial to investigate and evaluate the risks associated with LLMs before deploying them in critical infrastructure like smart grids. In this paper, we systematically evaluated the risks of LLMs and identified two major types of attacks relevant to potential smart grid LLM applications, presenting the corresponding threat models. We validated these attacks using popular LLMs and real smart grid data. Our validation demonstrates that attackers are capable of injecting bad data and retrieving domain knowledge from LLMs employed in different smart grid applications.
title Risks of Practicing Large Language Models in Smart Grid: Threat Modeling and Validation
topic Cryptography and Security
url https://arxiv.org/abs/2405.06237