Malicious Triggering False Data Injection Attack that Increases Smart Grid Scheduling Cost

Hezhong Pan; Fen Yuan; Peiyi Han; Shaoming Duan; Chuanyi Liu; Junbin Fang; Bin Zhou

doi:10.1109/DSC67331.2025.00013

Malicious Triggering False Data Injection Attack that Increases Smart Grid Scheduling Cost

Hezhong Pan
, Fen Yuan
, Peiyi Han
, Shaoming Duan
, Chuanyi Liu
, Junbin Fang^*
, Bin Zhou^*

^*Corresponding author for this work

Jinan University
Harbin Institute of Technology
Pengcheng Laboratory

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Countries around the world are accelerating the construction of smart grids based on renewable energy. Due to the difficulty and complexity of smart grids, data-driven intelligent power dispatch has become a core supporting technology, and data security has become even more crucial. False Data Injection (FDI) attack is the most common attack method that threatens the data security of smart grids. Defense methods based on AI models have been a major research trend in recent years. However, the vulnerability and false positive rates of AI models bring additional costs to the power system. This research focuses on the keyword 'COST': We constructed a threat model for AI-based FDI defense methods, proposed a Malicious Trigger Attack framework, and implemented an attack to increase the cost of AI-based FDI detection methods. The experiment shows that the framework significantly increases FDI defense costs in the power system, with Max-Rank MTD's operational costs increasing by 36. 91% and Robust MTD's by 117.79%.

Original language	English
Title of host publication	Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	33-40
Number of pages	8
ISBN (Electronic)	9798331579241
DOIs	https://doi.org/10.1109/DSC67331.2025.00013
State	Published - 2025
Externally published	Yes
Event	2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025 - Baoding, China Duration: 15 Aug 2025 → 17 Aug 2025

Publication series

Name	Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025

Conference

Conference	2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025
Country/Territory	China
City	Baoding
Period	15/08/25 → 17/08/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

AI based defense
false data injection attack
malicious trigger attack
smart grids
styling

Access to Document

10.1109/DSC67331.2025.00013

Cite this

Pan, H., Yuan, F., Han, P., Duan, S., Liu, C., Fang, J., & Zhou, B. (2025). Malicious Triggering False Data Injection Attack that Increases Smart Grid Scheduling Cost. In Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025 (pp. 33-40). (Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DSC67331.2025.00013

Pan, Hezhong ; Yuan, Fen ; Han, Peiyi et al. / Malicious Triggering False Data Injection Attack that Increases Smart Grid Scheduling Cost. Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025. Institute of Electrical and Electronics Engineers Inc., 2025. pp. 33-40 (Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025).

@inproceedings{d597a51479b2407fa125b270839aaf28,

title = "Malicious Triggering False Data Injection Attack that Increases Smart Grid Scheduling Cost",

abstract = "Countries around the world are accelerating the construction of smart grids based on renewable energy. Due to the difficulty and complexity of smart grids, data-driven intelligent power dispatch has become a core supporting technology, and data security has become even more crucial. False Data Injection (FDI) attack is the most common attack method that threatens the data security of smart grids. Defense methods based on AI models have been a major research trend in recent years. However, the vulnerability and false positive rates of AI models bring additional costs to the power system. This research focuses on the keyword 'COST': We constructed a threat model for AI-based FDI defense methods, proposed a Malicious Trigger Attack framework, and implemented an attack to increase the cost of AI-based FDI detection methods. The experiment shows that the framework significantly increases FDI defense costs in the power system, with Max-Rank MTD's operational costs increasing by 36. 91\% and Robust MTD's by 117.79\%.",

keywords = "AI based defense, false data injection attack, malicious trigger attack, smart grids, styling",

author = "Hezhong Pan and Fen Yuan and Peiyi Han and Shaoming Duan and Chuanyi Liu and Junbin Fang and Bin Zhou",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025 ; Conference date: 15-08-2025 Through 17-08-2025",

year = "2025",

doi = "10.1109/DSC67331.2025.00013",

language = "英语",

series = "Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "33--40",

booktitle = "Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025",

address = "美国",

}

Pan, H, Yuan, F, Han, P, Duan, S, Liu, C, Fang, J & Zhou, B 2025, Malicious Triggering False Data Injection Attack that Increases Smart Grid Scheduling Cost. in Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025. Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025, Institute of Electrical and Electronics Engineers Inc., pp. 33-40, 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025, Baoding, China, 15/08/25. https://doi.org/10.1109/DSC67331.2025.00013

Malicious Triggering False Data Injection Attack that Increases Smart Grid Scheduling Cost. / Pan, Hezhong; Yuan, Fen; Han, Peiyi et al.
Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025. Institute of Electrical and Electronics Engineers Inc., 2025. p. 33-40 (Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Malicious Triggering False Data Injection Attack that Increases Smart Grid Scheduling Cost

AU - Pan, Hezhong

AU - Yuan, Fen

AU - Han, Peiyi

AU - Duan, Shaoming

AU - Liu, Chuanyi

AU - Fang, Junbin

AU - Zhou, Bin

PY - 2025

Y1 - 2025

N2 - Countries around the world are accelerating the construction of smart grids based on renewable energy. Due to the difficulty and complexity of smart grids, data-driven intelligent power dispatch has become a core supporting technology, and data security has become even more crucial. False Data Injection (FDI) attack is the most common attack method that threatens the data security of smart grids. Defense methods based on AI models have been a major research trend in recent years. However, the vulnerability and false positive rates of AI models bring additional costs to the power system. This research focuses on the keyword 'COST': We constructed a threat model for AI-based FDI defense methods, proposed a Malicious Trigger Attack framework, and implemented an attack to increase the cost of AI-based FDI detection methods. The experiment shows that the framework significantly increases FDI defense costs in the power system, with Max-Rank MTD's operational costs increasing by 36. 91% and Robust MTD's by 117.79%.

AB - Countries around the world are accelerating the construction of smart grids based on renewable energy. Due to the difficulty and complexity of smart grids, data-driven intelligent power dispatch has become a core supporting technology, and data security has become even more crucial. False Data Injection (FDI) attack is the most common attack method that threatens the data security of smart grids. Defense methods based on AI models have been a major research trend in recent years. However, the vulnerability and false positive rates of AI models bring additional costs to the power system. This research focuses on the keyword 'COST': We constructed a threat model for AI-based FDI defense methods, proposed a Malicious Trigger Attack framework, and implemented an attack to increase the cost of AI-based FDI detection methods. The experiment shows that the framework significantly increases FDI defense costs in the power system, with Max-Rank MTD's operational costs increasing by 36. 91% and Robust MTD's by 117.79%.

KW - AI based defense

KW - false data injection attack

KW - malicious trigger attack

KW - smart grids

KW - styling

UR - https://www.scopus.com/pages/publications/105032991653

U2 - 10.1109/DSC67331.2025.00013

DO - 10.1109/DSC67331.2025.00013

M3 - 会议稿件

AN - SCOPUS:105032991653

T3 - Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025

SP - 33

EP - 40

BT - Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025

Y2 - 15 August 2025 through 17 August 2025

ER -

Pan H, Yuan F, Han P, Duan S, Liu C, Fang J et al. Malicious Triggering False Data Injection Attack that Increases Smart Grid Scheduling Cost. In Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025. Institute of Electrical and Electronics Engineers Inc. 2025. p. 33-40. (Proceedings - 2025 IEEE 10th International Conference on Data Science in Cyberspace, DSC 2025). doi: 10.1109/DSC67331.2025.00013

Malicious Triggering False Data Injection Attack that Increases Smart Grid Scheduling Cost

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this