Invisible Manipulation: Deep Reinforcement Learning-Enhanced Stealthy Attacks on Battery Energy Management Systems

This paper introduces an innovative cyber-attack scheme, “invisible manipulation,” utilizing timed-stealthy false data injection attacks (Timed-SFDIAs). By subtly altering critical measurements ahead of a target period, the attacker covertly steers system operations toward a sp...

Full description

Saved in:
Bibliographic Details
Main Authors: Qi Xiao, Lidong Song, Jong Ha Woo, Rongxing Hu, Bei Xu, Kai Ye, Ning Lu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11084779/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849728179111985152
author Qi Xiao
Lidong Song
Jong Ha Woo
Rongxing Hu
Bei Xu
Kai Ye
Ning Lu
author_facet Qi Xiao
Lidong Song
Jong Ha Woo
Rongxing Hu
Bei Xu
Kai Ye
Ning Lu
author_sort Qi Xiao
collection DOAJ
description This paper introduces an innovative cyber-attack scheme, &#x201C;invisible manipulation,&#x201D; utilizing timed-stealthy false data injection attacks (Timed-SFDIAs). By subtly altering critical measurements ahead of a target period, the attacker covertly steers system operations toward a specific failure state, evading detection while enabling repeated attacks over time. Using Battery Energy Management System (BEMS) as a case study, we demonstrate the scheme&#x2019;s effectiveness in manipulating Battery Energy Storage Systems (BESS), critical for grids with high renewable penetration. Our method employs deep reinforcement learning (DRL) to generate synthetic measurements (e.g., battery voltage, current) that mimic real data, bypassing residual-based bad data detection (BDD) and misleading Extended Kalman-filter (EKF) based State-of-Charge (SoC) estimations. This allows the BEMS to operate the BESS per the attacker&#x2019;s objectives. To minimize real-time computational demands, we transform this online optimization problem into an offline DRL training problem, utilizing high-fidelity simulation data from a digital twin-based microgrid testbed. The testbed incorporates real load and solar generation profiles with BESS models in the electromagnetic transient (EMT) domain at a 100-<inline-formula> <tex-math notation="LaTeX">$\mu $ </tex-math></inline-formula>s resolution, capturing rapid system dynamics and ensuring robust performance in real-time scenarios. Testing on the same testbed allows real-time evaluation of microgrid responses, where the BEMS, EKF-based SoC estimation algorithms interact dynamically with the injected false measurements. This unique DRL training and testing setup not only showcases the effectiveness of the Timed-SFDIA algorithm in evading detection and achieving diverse attack objectives but also underscores the critical role of high-fidelity, digital-twin based real-time simulation testbeds. Such testbeds are invaluable for training and validating data-driven machine learning algorithms, especially when field tests and real-world validation are challenging to conduct, as they ensure robustness and adaptability under realistic operational conditions.
format Article
id doaj-art-68fbb0dccc8040f7a3c51c06abdf3a29
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-68fbb0dccc8040f7a3c51c06abdf3a292025-08-20T03:09:37ZengIEEEIEEE Access2169-35362025-01-011313150913152410.1109/ACCESS.2025.359043711084779Invisible Manipulation: Deep Reinforcement Learning-Enhanced Stealthy Attacks on Battery Energy Management SystemsQi Xiao0https://orcid.org/0009-0005-3365-2392Lidong Song1Jong Ha Woo2Rongxing Hu3Bei Xu4https://orcid.org/0009-0009-3709-3099Kai Ye5https://orcid.org/0009-0003-5955-805XNing Lu6https://orcid.org/0000-0003-0125-0653Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USADepartment of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USADepartment of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USADepartment of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USADepartment of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USADepartment of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USADepartment of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USAThis paper introduces an innovative cyber-attack scheme, &#x201C;invisible manipulation,&#x201D; utilizing timed-stealthy false data injection attacks (Timed-SFDIAs). By subtly altering critical measurements ahead of a target period, the attacker covertly steers system operations toward a specific failure state, evading detection while enabling repeated attacks over time. Using Battery Energy Management System (BEMS) as a case study, we demonstrate the scheme&#x2019;s effectiveness in manipulating Battery Energy Storage Systems (BESS), critical for grids with high renewable penetration. Our method employs deep reinforcement learning (DRL) to generate synthetic measurements (e.g., battery voltage, current) that mimic real data, bypassing residual-based bad data detection (BDD) and misleading Extended Kalman-filter (EKF) based State-of-Charge (SoC) estimations. This allows the BEMS to operate the BESS per the attacker&#x2019;s objectives. To minimize real-time computational demands, we transform this online optimization problem into an offline DRL training problem, utilizing high-fidelity simulation data from a digital twin-based microgrid testbed. The testbed incorporates real load and solar generation profiles with BESS models in the electromagnetic transient (EMT) domain at a 100-<inline-formula> <tex-math notation="LaTeX">$\mu $ </tex-math></inline-formula>s resolution, capturing rapid system dynamics and ensuring robust performance in real-time scenarios. Testing on the same testbed allows real-time evaluation of microgrid responses, where the BEMS, EKF-based SoC estimation algorithms interact dynamically with the injected false measurements. This unique DRL training and testing setup not only showcases the effectiveness of the Timed-SFDIA algorithm in evading detection and achieving diverse attack objectives but also underscores the critical role of high-fidelity, digital-twin based real-time simulation testbeds. Such testbeds are invaluable for training and validating data-driven machine learning algorithms, especially when field tests and real-world validation are challenging to conduct, as they ensure robustness and adaptability under realistic operational conditions.https://ieeexplore.ieee.org/document/11084779/Cyber-physical attacksdeep reinforcement learningtimed stealthy false data injection (SFDIA)invisible manipulation attacksstate-of-charge (SoC) estimation
spellingShingle Qi Xiao
Lidong Song
Jong Ha Woo
Rongxing Hu
Bei Xu
Kai Ye
Ning Lu
Invisible Manipulation: Deep Reinforcement Learning-Enhanced Stealthy Attacks on Battery Energy Management Systems
IEEE Access
Cyber-physical attacks
deep reinforcement learning
timed stealthy false data injection (SFDIA)
invisible manipulation attacks
state-of-charge (SoC) estimation
title Invisible Manipulation: Deep Reinforcement Learning-Enhanced Stealthy Attacks on Battery Energy Management Systems
title_full Invisible Manipulation: Deep Reinforcement Learning-Enhanced Stealthy Attacks on Battery Energy Management Systems
title_fullStr Invisible Manipulation: Deep Reinforcement Learning-Enhanced Stealthy Attacks on Battery Energy Management Systems
title_full_unstemmed Invisible Manipulation: Deep Reinforcement Learning-Enhanced Stealthy Attacks on Battery Energy Management Systems
title_short Invisible Manipulation: Deep Reinforcement Learning-Enhanced Stealthy Attacks on Battery Energy Management Systems
title_sort invisible manipulation deep reinforcement learning enhanced stealthy attacks on battery energy management systems
topic Cyber-physical attacks
deep reinforcement learning
timed stealthy false data injection (SFDIA)
invisible manipulation attacks
state-of-charge (SoC) estimation
url https://ieeexplore.ieee.org/document/11084779/
work_keys_str_mv AT qixiao invisiblemanipulationdeepreinforcementlearningenhancedstealthyattacksonbatteryenergymanagementsystems
AT lidongsong invisiblemanipulationdeepreinforcementlearningenhancedstealthyattacksonbatteryenergymanagementsystems
AT jonghawoo invisiblemanipulationdeepreinforcementlearningenhancedstealthyattacksonbatteryenergymanagementsystems
AT rongxinghu invisiblemanipulationdeepreinforcementlearningenhancedstealthyattacksonbatteryenergymanagementsystems
AT beixu invisiblemanipulationdeepreinforcementlearningenhancedstealthyattacksonbatteryenergymanagementsystems
AT kaiye invisiblemanipulationdeepreinforcementlearningenhancedstealthyattacksonbatteryenergymanagementsystems
AT ninglu invisiblemanipulationdeepreinforcementlearningenhancedstealthyattacksonbatteryenergymanagementsystems