Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

ChatGPT and Other Large Language Models for Cybersecurity of Smart Grid Applications

Conference ·
; ; ;
Cybersecurity breaches targeting electrical substations constitute a significant threat to the integrity of the power grid, necessitating comprehensive defense and mitigation strategies. Any anomaly in information and communication technology (ICT) should be detected for secure communications between devices in digital substations. This paper proposes large language models (LLMs), e.g., ChatGPT, for the cybersecurity of IEC 61850-based communications. Multi-cast messages such as generic object oriented system events (GOOSE) and sampled values (SV) are used for case studies. The proposed LLM-based cybersecurity framework includes, for the first time, data pre-processing of communication systems and human-in-the-loop (HITL) training (considering the cybersecurity guidelines recommended by humans). The results show a comparative analysis of detected anomaly data carried out based on the performance evaluation metrics for different LLMs. A hardware-in-the-loop (HIL) testbed is used to generate and extract a dataset of IEC 61850 communications.
Research Organization:
National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Sponsoring Organization:
USDOE National Renewable Energy Laboratory (NREL)
DOE Contract Number:
AC36-08GO28308
OSTI ID:
2477400
Report Number(s):
NREL/CP-5D00-92062; MainId:93840; UUID:88d586a1-a4cb-416e-a4dc-acadd3520018; MainAdminId:74243
Country of Publication:
United States
Language:
English

References (9)

A novel hybrid methodology to secure GOOSE messages against cyberattacks in smart grids journal February 2023
Anomaly Detection for Cybersecurity of the Substations journal December 2011
ChatGPT: Vision and challenges journal January 2023
A Deep Learning-Based Cyberattack Detection System for Transmission Protective Relays journal May 2021
Cyber Attacks on Power Grids: Causes and Propagation of Cascading Failures journal January 2023
From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy journal January 2023
ERENO: A Framework for Generating Realistic IEC–61850 Intrusion Detection Datasets for Smart Grids journal July 2024
Unsupervised Learning based Intrusion Detection for GOOSE Messages in Digital Substation conference December 2022
Automated Cybersecurity Tester for IEC61850-Based Digital Substations journal October 2022

Similar Records

Data-Centric Communication Framework for Multicast IEC 61850 Routable GOOSE Messages over the WAN in Modern Power Systems
Journal Article · Fri Jan 24 19:00:00 EST 2020 · Applied Sciences · OSTI ID:1801316
Assessment of the Electrical Substation-Grid Testbed with Inside/Outside Devices and Distributed Ledger Technology
Technical Report · Fri Apr 01 00:00:00 EDT 2022 · OSTI ID:1864423
Detection of DoS Attacks Using ARFIMA Modeling of GOOSE Communication in IEC 61850 Substations
Journal Article · Wed Sep 30 20:00:00 EDT 2020 · Energies · OSTI ID:1850594

Related Subjects

ChatGPT
MATHEMATICS AND COMPUTING
POWER TRANSMISSION AND DISTRIBUTION
cybersecurity
generic object oriented system event (GOOSE)
human-in-the-loop (HITL)
large language model (LLM)
sampled value (SV)
substations