Applying Large Language Models to Power Systems: Potential Security Threats

被引：20

作者：

Ruan, Jiaqi ^{[1
]}

Liang, Gaoqi ^{[2
]}

Zhao, Huan ^{[3
]}

Liu, Guolong ^{[4
]}

Sun, Xianzhuo ^{[1
]}

Qiu, Jing ^{[5
]}

Xu, Zhao ^{[6
,7
]}

Wen, Fushuan ^{[8
]}

Dong, Zhao Yang ^{[3
]}

机构：

[1] Hong Kong Polytech Univ, Dept Elect & Elect Engn, Hong Kong, Peoples R China

[2] Harbin Inst Technol Shenzhen, Sch Mech Engn & Automat, Shenzhen 518055, Peoples R China

[3] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore

[4] Chinese Univ Hong Kong Shenzhen, Sch Sci & Engn, Shenzhen 518172, Peoples R China

[5] Univ Sydney, Sch Elect & Informat Engn, Sydney, NSW 2006, Australia

[6] Hong Kong Polytech Univ, Dept Elect & Elect Engn, Hong Kong, Peoples R China

[7] Hong Kong Polytech Univ, Res Inst Smart Energy, Hong Kong, Peoples R China

[8] Zhejiang Univ, Coll Elect Engn, Hangzhou 310027, Peoples R China

来源：

IEEE TRANSACTIONS ON SMART GRID | 2024年 / 15卷 / 03期

关键词：

Power system stability; Security; Decision making; Training; Semantics; Reliability; Real-time systems; Power systems; large language models; security threats;

D O I：

10.1109/TSG.2024.3373256

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Applying large language models (LLMs) to modern power systems presents a promising avenue for enhancing decision-making and operational efficiency. However, this action may also incur potential security threats, which have not been fully recognized so far. To this end, this article analyzes potential threats incurred by applying LLMs to power systems, emphasizing the need for urgent research and development of countermeasures.

引用

页码：3333 / 3336

页数：4

共 12 条

[1] On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? [J].

Bender, Emily M. ;

Gebru, Timnit ;

McMillan-Major, Angelina ;

Shmitchell, Shmargaret .

PROCEEDINGS OF THE 2021 ACM CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, FACCT 2021, 2021, :610-623

[2]

Carlini N, 2021, PROCEEDINGS OF THE 30TH USENIX SECURITY SYMPOSIUM, P2633

[3] A Survey of Denial-of-Service Attacks and Solutions in the Smart Grid [J].

Huseinovic, Alvin ;

Mrdovic, Sasa ;

Bicakci, Kemal ;

Uludag, Suleyman .

IEEE ACCESS, 2020, 8 :177447-177470

[4] A Review of False Data Injection Attacks Against Modern Power Systems [J].

Liang, Gaoqi ;

Zhao, Junhua ;

Luo, Fengji ;

Weller, Steven R. ;

Dong, Zhao Yang .

IEEE TRANSACTIONS ON SMART GRID, 2017, 8 (04) :1630-1638

[5] AUTOGEN: A Personalized Large Language Model for Academic Enhancement-Ethics and Proof of Principle [J].

Mann, Sebastian Porsdam ;

Earp, Brian D. ;

Moller, Nikolaj ;

Vynn, Suren ;

Savulescu, Julian .

AMERICAN JOURNAL OF BIOETHICS, 2023, 23 (10) :28-41

[6] Deep learning for cybersecurity in smart grids: Review and perspectives [J].

Ruan, Jiaqi ;

Liang, Gaoqi ;

Zhao, Junhua ;

Zhao, Huan ;

Qiu, Jing ;

Wen, Fushuan ;

Dong, Zhao Yang .

ENERGY CONVERSION AND ECONOMICS, 2023, 4 (04) :233-251

[7] Super-Resolution Perception Assisted Spatiotemporal Graph Deep Learning Against False Data Injection Attacks in Smart Grid [J].

Ruan, Jiaqi ;

Fan, Gang ;

Zhu, Yifan ;

Liang, Gaoqi ;

Zhao, Junhua ;

Wen, Fushuan ;

Dong, Zhao Yang .

IEEE TRANSACTIONS ON SMART GRID, 2023, 14 (05) :4035-4046

[8] Event-based secure H∞ load frequency control for delayed power systems subject to deception attacks [J].

Wang, Dongji ;

Chen, Fei ;

Meng, Bo ;

Hu, Xingliu ;

Wang, Jing .

APPLIED MATHEMATICS AND COMPUTATION, 2021, 394

[9] Dynamic Data Injection Attack Detection of Cyber Physical Power Systems With Uncertainties [J].

Wang, Huaizhi ;

Ruan, Jiaqi ;

Zhou, Bin ;

Li, Canbing ;

Wu, Qiuwei ;

Raza, Muhammad Qamar ;

Cao, Guang-Zhong .

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2019, 15 (10) :5505-5518

[10]

Weidinger L, 2022, PROCEEDINGS OF 2022 5TH ACM CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, FACCT 2022, P214, DOI 10.1145/3531146.3533088

← 1 2 →