Abstract
Under current zero-trust security architectures, real-time hot patching of power field equipment remains constrained by three critical technological limitations: excessive authentication latency that violates millisecond-level control requirements, the lack of quantitative mechanisms to prevent runtime structural disorder during patch injection, and the absence of effective integration between human operational expertise and automated decision systems. These limitations make existing zero-trust and fully automated hot patching approaches unsuitable for safety-critical power equipment operating under strict real-time and fault-intolerant conditions. To address these gaps, this paper proposes a brain–computer co-evolution–driven negative entropy zero-trust hot patching framework. Compared with conventional zero-trust implementations and automated reinforcement learning–based patching strategies, the proposed method introduces human EEG-derived risk intuition into the security decision loop and establishes a multidimensional negative entropy model to explicitly quantify and constrain system structural order during runtime updates. By combining these mechanisms with millisecond-level eBPF-based atomic code replacement, the framework aligns strong security verification with real-time operational constraints. Experimental results on an RTDS simulation platform and a real IED cluster (1,200 hot patching operations) demonstrate that the proposed framework reduces high-risk security decision latency to 12.3 ms—significantly lower than current zero-trust baselines—while limiting entropy increase risk to 3.5% and maintaining 99.99% service availability. These results indicate that the proposed approach bridges a critical gap between current zero-trust standards and the practical requirements of real-time, safety-critical power equipment updates.
Data availability
The data that support the findings of this study are openly available in Science Data Bank at https://doi.org/10.57760/sciencedb.28813.
References
Murtaza, A. A. et al. Paradigm shift for predictive maintenance and condition monitoring from Industry 4.0 to Industry 5.0: A systematic review, challenges and case study. Results Eng. 24, 102935 (2024).
Ledmaoui, Y., El Maghraoui, A., El Aroussi, M. & Saadane, R. Review of Recent Advances in Predictive Maintenance and Cybersecurity for Solar Plants. Sensors 25 (1), 206 (2025).
Suresh, K. P., Senthilkumar, R., Saravanan, S., Suresh, M. & Jamuna, P. Challenges and Opportunities for Predictive Maintenance of Solar Plants 65–83 (Photovoltaic Systems, 2022).
Geng, S. & Wang, X. Predictive maintenance scheduling for multiple power equipment based on data-driven fault prediction. Comput. Ind. Eng. 164, 107898 (2022).
Schwartz, J. A., Ricks, W., Kolemen, E. & Jenkins, J. D. Valuing maintenance strategies for fusion plants as part of a future electricity grid. arXiv preprint arXiv :240501514. (2024).
Salehi, M. & Pattabiraman, K. AutoPatch: Automated Generation of Hotpatches for Real-Time Embedded Devices. In Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security (pp. 2370–2384). (2024, December).
Xi, Z., Zhang, B., Bhattacharjya, A., Wang, Y. & He, C. Research on a Secure and Reliable Runtime Patching Method for Cyber–Physical Systems and Internet of Things Devices. Symmetry 17 (7), 983 (2025).
Wang, M. et al. Study on the Preparation and Aging Performance of Temperature-Indicating Patch Used for Thermal Defect Detection of Transformer Bushing Cylinder Head. Processes 12 (4), 736 (2024).
Lickert, H., Lachnit, T. & Dietrich, F. Approach for Structured Repairability Assessment for Automated Repair Processes. In Global Conference on Sustainable Manufacturing (pp. 391–398). Cham: Springer Nature Switzerland. (2023, December).
Al Ameeri, T. A., Ab Rahman, M. N. & Muhamad, N. Analysing effective and ineffective impacts of maintenance strategies on electric power plants: A comprehensive approach. Energies 16 (17), 6243 (2023).
Dissanayake, N., Zahedi, M., Jayatilaka, A. & Babar, M. A. Why, how and where of delays in software security patch management: An empirical investigation in the healthcare sector. Proceedings of the ACM on Human-computer Interaction, 6(CSCW2), 1–29. (2022).
Wetzels, J., Dos Santos, D. & Ghafari, M. Insecure by design in the backbone of critical infrastructure. In Proceedings of Cyber-Physical Systems and Internet of Things Week 2023 (pp. 7–12). (2023).
Dissanayake, N., Jayatilaka, A., Zahedi, M. & Babar, M. A. Software security patch management-A systematic literature review of challenges, approaches, tools and practices. Inf. Softw. Technol. 144, 106771 (2022).
Adinolfi, G., Ciavarella, R., Graditi, G., Ricca, A. & Valenti, M. Innovative Method for Reliability Assessment of Power Systems: From Components Modeling to Key Indicators Evaluation. Electronics 13 (2), 275 (2024).
Jalilian, A., Taheri, B. & Molzahn, D. K. Co-Optimization of Damage Assessment and Restoration: A Resilience-Driven Dynamic Crew Allocation for Power Distribution Systems. IEEE Trans. Power Syst. 40 (1), 676–688 (2024).
Ul Haq, S., Singh, Y., Sharma, A., Gupta, R. & Gupta, D. A survey on IoT & embedded device firmware security: architecture, extraction techniques, and vulnerability analysis frameworks. Discover Internet Things. 3 (1), 17 (2023).
Urblik, L., Kajati, E., Papcun, P. & Zolotová, I. Containerization in edge intelligence: A review. Electronics 13 (7), 1335 (2024).
Liu, C. et al. Dissecting zero trust: Research landscape and its implementation in IoT. Cybersecurity 7 (1), 20 (2024).
Molęda, M., Małysiak-Mrozek, B., Ding, W., Sunderam, V. & Mrozek, D. From corrective to predictive maintenance—A review of maintenance approaches for the power industry. Sensors 23 (13), 5970 (2023).
Mohsin, A., Janicke, H., Ibrahim, A., Sarker, I. H. & Camtepe, S. A Unified Framework for Human AI Collaboration in Security Operations Centers with Trusted Autonomy. (2025). arXiv preprint arXiv:2505.23397.
Huang, Z., Sheng, Z., Ma, C. & Chen, S. Human as AI mentor: Enhanced human-in-the-loop reinforcement learning for safe and efficient autonomous driving. Commun. Transp. Res. 4, 100127 (2024).
Karunamurthy, A., Kiruthivasan, R. & Gauthamkrishna, S. Human-in-the-loop intelligence: Advancing AI-centric cybersecurity for the future. Quing: Int. J. Multidisciplinary Sci. Res. Dev. 2 (3), 20–43 (2023).
Alahaideb, L., Al-Nafjan, A., Aljumah, H. & Aldayel, M. Brain–Computer Interface for EEG-Based Authentication: Advancements and Practical Implications. Sensors 25 (16), 4946 (2025).
Seyfizadeh, A. et al. Enhancing security in brain–computer interface applications with deep learning: Electroencephalogram-based user identification. Expert Syst. Appl. 253, 124218 (2024).
Brocal, F. Brain-computer interfaces in safety and security fields: risks and applications. Saf. Sci. 160, 106051 (2023).
Yu, H. et al. Lyapunov exponents and Lagrangian chaos suppression in compressible homogeneous isotropic turbulence. Phys. Fluids, 35(12). (2023):125114-125114.
Winter, L., Taylor, P., Bellenger, C., Grimshaw, P. & Crowther, R. G. The application of the Lyapunov Exponent to analyse human performance: A systematic review. J. Sports Sci. 41 (22), 1994–2013 (2023).
Zhang, Y. C. & Zhang, Y. Y. Lyapunov exponent, mobility edges, and critical region in the generalized Aubry-André model with an unbounded quasiperiodic potential. Phys. Rev. B. 105 (17), 174206 (2022).
Irani, H. & Metsis, V. Enhancing time-series prediction with temporal context modeling: A Bayesian and deep learning synergy. In The International FLAIRS Conference Proceedings (Vol. 37). (2024).
Nikookar, S., Namazi Nia, S., Basu Roy, S., Amer-Yahia, S. & Omidvar-Tehrani, B. Model reusability in Reinforcement Learning. VLDB J. 34 (4), 41 (2025).
Abolfathi, M., Inturi, S., Banaei-Kashani, F. & Jafarian, J. H. Toward enhancing web privacy on HTTPS traffic: A novel SuperLearner attack model and an efficient defense approach with adversarial examples. Computers Secur. 139, 103673 (2024).
Vaziri, A. & Fang, H. Optimal inferential control of convolutional neural networks. In 2025 American Control Conference (ACC) (pp. 2603–2610). IEEE. (2025), July.
Aqajari, S. A. H. Robust, Personalized, and Context-Aware Affect Monitoring in Daily-Life (Doctoral dissertation, University of California, Irvine). (2024).
Choudhry, A. et al. Integration of EEG-based BCI Technology in IoT enabled Smart Home Environment: An in-depth comparative analysis on Human-Computer Interaction Techniques. (2025). Expert Systems with Applications, 128730.
Qi, Y. et al. Dynamic ensemble Bayesian filter for robust control of a human brain-machine interface. IEEE Trans. Biomed. Eng. 69 (12), 3825–3835 (2022).
Ma, Q. et al. Directly wireless communication of human minds via non-invasive brain-computer-metasurface platform. elight 2 (1), 11 (2022).
Wang, R., Li, C., Zhang, K. & Tu, B. Zero-trust based dynamic access control for cloud computing. Cybersecurity 8 (1), 12 (2025).
Wu, X. et al. Hi-SAM: A high-scalable authentication model for satellite-ground Zero-Trust system using mean field game. J. Netw. Syst. Manage. 33 (3), 72 (2025).
Yeoh, W., Liu, M., Shore, M. & Jiang, F. Zero trust cybersecurity: Critical success factors and a maturity assessment framework. Computers Secur. 133, 103412 (2023).
Liu, Y., Lan, Y. & Xia, Y. The evolutionary mechanism of information negentropy spurred by emergencies. Sci. Rep. 15 (1), 31886 (2025).
Durán, O., Sáez, G. & Durán, P. Negentropy as a Measure to Evaluate the Resilience in Industrial Plants. Mathematics 11 (12), 2707 (2023).
Liu, S. & Motani, M. Improving Mutual Information based Feature Selection by Boosting Unique Relevance. J. Artif. Intell. Res. 82, 1267–1292 (2025).
Gowri, G., Lun, X., Klein, A. & Yin, P. Approximating mutual information of high-dimensional variables using learned representations. Adv. Neural. Inf. Process. Syst. 37, 132843–132875 (2024).
Tuononen, M. & Hautamäki, V. Improving Numerical Stability of Normalized Mutual Information Estimator on High Dimensions (IEEE Signal Processing Letters, 2025).
Roveda, L., Testa, A., Shahid, A. A., Braghin, F. & Piga, D. Q-Learning-based model predictive variable impedance control for physical human-robot collaboration. Artif. Intell. 312, 103771 (2022).
Islam, M. S. et al. Human-AI collaboration in real-world complex environment with reinforcement learning. Neural Comput. Appl., 37,1–31. (2025).
Korivand, S., Galvani, G., Ajoudani, A., Gong, J. & Jalili, N. Optimizing Human–Robot Teaming Performance through Q-Learning-Based Task Load Adjustment and Physiological Data Analysis. Sensors 24 (9), 2817 (2024).
Ma, H., Vo, T. V. & Leong, T. Y. Hierarchical Reinforcement Learning with Human-AI Collaborative Sub-Goals Optimization. In Proceedings of the 2023 international conference on autonomous agents and multiagent systems (pp. 2310–2312). (2023).
Gu, S. et al. A human-centered safe robot reinforcement learning framework with interactive behaviors. Front. Neurorobotics. 17, 1280341 (2023).
Huang, K. et al. SoK: Challenges and Paths Toward Memory Safety for eBPF. In 2025 IEEE Symposium on Security and Privacy (SP) (pp. 848–866). IEEE. (2025).
Craun, M., Oswald, A. & Williams, D. Enabling eBPF on Embedded Systems Through Decoupled Verification. In Proceedings of the 1st Workshop on eBPF and Kernel Extensions (pp. 63–69). (2023).
Wang, Z. et al. When eBPF Meets Machine Learning: On-the-fly OS Kernel Compartmentalization. arXiv preprint arXiv:2401.05641. (2024).
Funding
This work was supported by the Science and Technology Project of State Grid Xinjiang Electric Power Co., Ltd. [grant number: SGXJDK00DWJS2500136]
Author information
Authors and Affiliations
Contributions
Zou Z W: Conceptualization, Experiments, Writing-Original Draft, Revision.Wang B: Data Curation, Formal Analysis, Writing-Review & Editing.Chen T: Supervision, Funding Acquisition, Writing-Review & EditingFan S M: Visualization, MethodologyYe B: Model Design, Project Administration.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethics, Consent to Participate, and Consent to Publish declarations
This study was approved by the Ethics Committee of State Grid Xinjiang Electric Power Co., Ltd. All methods were performed in accordance with the relevant guidelines and regulations, including the Declaration of Helsinki and the policies of this ethics committee. Informed consent was obtained from all participants in accordance with ethical standards. Participants were fully informed of their rights, and a sample consent form was available upon request. All participants were adults.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Zou, Z., Wang, B., Chen, T. et al. A brain–edge co-evolution framework for zero-trust real-time hot patching in power equipment. Sci Rep (2026). https://doi.org/10.1038/s41598-026-45643-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-45643-6
