Multistage adaptive cyberattack in power systems with CNN identification feedback loops

Abstract The increasing integration of digital technologies in hybrid hydrogen-power networks has introduced new cybersecurity vulnerabilities that existing static or single-phase cyberattack models fail to adequately exploit or defend against. These models typically lack dynamic adaptability, coord...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohannad Alhazmi, Alexis Pengfei Zhao, Xi Cheng, Chenlu Yang
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-10582-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849344146573099008
author Mohannad Alhazmi
Alexis Pengfei Zhao
Xi Cheng
Chenlu Yang
author_facet Mohannad Alhazmi
Alexis Pengfei Zhao
Xi Cheng
Chenlu Yang
author_sort Mohannad Alhazmi
collection DOAJ
description Abstract The increasing integration of digital technologies in hybrid hydrogen-power networks has introduced new cybersecurity vulnerabilities that existing static or single-phase cyberattack models fail to adequately exploit or defend against. These models typically lack dynamic adaptability, coordination across multiple attack stages, and obfuscation mechanisms, thereby limiting their effectiveness and realism. To address this gap, we propose a novel Cyberattack Design Based on CNN-DQN-Blockchain Technology for Targeted Adaptive Strategy (CDB-TAS)—a three-stage, dynamically evolving cyberattack framework tailored for hybrid hydrogen-electric networks. The proposed CDB-TAS model comprises: (i) a Preliminary Reconnaissance Phase, where a Convolutional Neural Network (CNN) identifies the most vulnerable buses via real-time anomaly detection; (ii) an Escalation Phase, where a Double Deep Q-Network (Double DQN) dynamically refines the attack strategy based on grid response and demand profiles; and (iii) a Sustained Attack Phase, which maintains high-intensity disruptions while minimizing detection through continuous feedback adaptation. Additionally, a private blockchain network is employed not for defense, but as an attacker-side obfuscation layer—concealing attack metadata and enabling decentralized coordination among malicious nodes. Simulations on a synthetic 2000-bus hybrid hydrogen-power system modeled after ERCOT reveal that CDB-TAS induces up to 15% voltage drop at critical buses (e.g., Bus 3103), disrupts over 600 MW of load across 50 substations, and achieves 23.4% higher disruption efficiency with lower anomaly detection rates compared to baseline attacks. This study presents the first integrated framework combining CNN, reinforcement learning, and blockchain from an adversarial perspective, offering new insights into the evolving threat landscape and guiding the development of future cyber-resilience strategies in multi-energy systems.
format Article
id doaj-art-b54ecf11c6dd47889ab9e184bfbfab5d
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-b54ecf11c6dd47889ab9e184bfbfab5d2025-08-20T03:42:44ZengNature PortfolioScientific Reports2045-23222025-07-0115111710.1038/s41598-025-10582-1Multistage adaptive cyberattack in power systems with CNN identification feedback loopsMohannad Alhazmi0Alexis Pengfei Zhao1Xi Cheng2Chenlu Yang3Electrical Engineering Department, College of Applied Engineering, King Saud UniversityDepartment of Energy Science and Engineering, Stanford Doerr School of Sustainability, Stanford UniversityDepartment of Civil and Environmental Engineering, University of California at BerkeleyDepartment of Chemistry and Chemical Biology, Cornell UniversityAbstract The increasing integration of digital technologies in hybrid hydrogen-power networks has introduced new cybersecurity vulnerabilities that existing static or single-phase cyberattack models fail to adequately exploit or defend against. These models typically lack dynamic adaptability, coordination across multiple attack stages, and obfuscation mechanisms, thereby limiting their effectiveness and realism. To address this gap, we propose a novel Cyberattack Design Based on CNN-DQN-Blockchain Technology for Targeted Adaptive Strategy (CDB-TAS)—a three-stage, dynamically evolving cyberattack framework tailored for hybrid hydrogen-electric networks. The proposed CDB-TAS model comprises: (i) a Preliminary Reconnaissance Phase, where a Convolutional Neural Network (CNN) identifies the most vulnerable buses via real-time anomaly detection; (ii) an Escalation Phase, where a Double Deep Q-Network (Double DQN) dynamically refines the attack strategy based on grid response and demand profiles; and (iii) a Sustained Attack Phase, which maintains high-intensity disruptions while minimizing detection through continuous feedback adaptation. Additionally, a private blockchain network is employed not for defense, but as an attacker-side obfuscation layer—concealing attack metadata and enabling decentralized coordination among malicious nodes. Simulations on a synthetic 2000-bus hybrid hydrogen-power system modeled after ERCOT reveal that CDB-TAS induces up to 15% voltage drop at critical buses (e.g., Bus 3103), disrupts over 600 MW of load across 50 substations, and achieves 23.4% higher disruption efficiency with lower anomaly detection rates compared to baseline attacks. This study presents the first integrated framework combining CNN, reinforcement learning, and blockchain from an adversarial perspective, offering new insights into the evolving threat landscape and guiding the development of future cyber-resilience strategies in multi-energy systems.https://doi.org/10.1038/s41598-025-10582-1Blockchain technologyConvolutional neural networksCyberattack simulationCybersecurity in energy systemsData integrity and anonymityDouble deep Q-networks
spellingShingle Mohannad Alhazmi
Alexis Pengfei Zhao
Xi Cheng
Chenlu Yang
Multistage adaptive cyberattack in power systems with CNN identification feedback loops
Scientific Reports
Blockchain technology
Convolutional neural networks
Cyberattack simulation
Cybersecurity in energy systems
Data integrity and anonymity
Double deep Q-networks
title Multistage adaptive cyberattack in power systems with CNN identification feedback loops
title_full Multistage adaptive cyberattack in power systems with CNN identification feedback loops
title_fullStr Multistage adaptive cyberattack in power systems with CNN identification feedback loops
title_full_unstemmed Multistage adaptive cyberattack in power systems with CNN identification feedback loops
title_short Multistage adaptive cyberattack in power systems with CNN identification feedback loops
title_sort multistage adaptive cyberattack in power systems with cnn identification feedback loops
topic Blockchain technology
Convolutional neural networks
Cyberattack simulation
Cybersecurity in energy systems
Data integrity and anonymity
Double deep Q-networks
url https://doi.org/10.1038/s41598-025-10582-1
work_keys_str_mv AT mohannadalhazmi multistageadaptivecyberattackinpowersystemswithcnnidentificationfeedbackloops
AT alexispengfeizhao multistageadaptivecyberattackinpowersystemswithcnnidentificationfeedbackloops
AT xicheng multistageadaptivecyberattackinpowersystemswithcnnidentificationfeedbackloops
AT chenluyang multistageadaptivecyberattackinpowersystemswithcnnidentificationfeedbackloops