{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,12]],"date-time":"2026-11-12T18:18:30Z","timestamp":1794507510370,"version":"4.9.1"},"reference-count":47,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Cybersecurity Authority","award":["No. CRPG-25-3152"],"award-info":[{"award-number":["No. CRPG-25-3152"]}]},{"DOI":"10.13039\/501100002383","name":"King Saud University","doi-asserted-by":"crossref","award":["ORF-2025-636"],"award-info":[{"award-number":["ORF-2025-636"]}],"id":[{"id":"10.13039\/501100002383","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The transition from traditional power systems to smart grids demands advanced methods for detecting and classifying Power Quality Disturbances (PQDs)\u2014variations in voltage, current, or frequency that disrupt device performance. The rise of renewable energy and nonlinear loads, such as LED lighting, has increased PQD occurrences. While deep learning models can effectively analyze data from grid sensors to detect PQD occurrences, privacy concerns often prevent operators from sharing raw data which is necessary to train the models. To address this, Federated Learning (FL) enables collaborative model training without exposing sensitive information. However, FL\u2019s decentralized design introduces new risks, particularly data poisoning attacks, where malicious clients corrupt model updates to degrade the global model accuracy. Despite these risks, PQD classification under FL and its vulnerability to such attacks remain largely unexplored. In this work, we develop FL-based classifiers for PQD detection and compare their performance to traditionally trained, centralized models. As expected from prior FL research, we observed a slight drop in performance: the model\u2019s accuracy decreased from 97% (centralized) to 96% (FL), while the false alarm rate increased from 0.19% to 4%. We also emulate five poisoning scenarios, including indiscriminate attacks aimed at degrading model accuracy and class-specific attacks intended to hide particular disturbance types. Our experimental results show that the attacks are very successful in reducing the accuracy of the classifier. Furthermore, we implement a detection mechanism designed to identify and isolate corrupted client updates, preventing them from influencing the global model. Experimental results reveal that our defense substantially curtails the performance degradation induced by poisoned updates, thereby preserving the robustness of the global model against adversarial influence.<\/jats:p>","DOI":"10.3390\/s25226880","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T12:44:55Z","timestamp":1762865095000},"page":"6880","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Robust Federated-Learning-Based Classifier for Smart Grid Power Quality Disturbances"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8601-3184","authenticated-orcid":false,"given":"Maazen","family":"Alsabaan","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh 11451, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdelrhman","family":"Elsayed","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Tennessee Tech University, Cookeville, TN 38505, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6790-8310","authenticated-orcid":false,"given":"Atef","family":"Bondok","sequence":"additional","affiliation":[{"name":"Computer Science, Eastern Connecticut State University, Windham, CT 06226, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8986-001X","authenticated-orcid":false,"given":"Mahmoud M.","family":"Badr","sequence":"additional","affiliation":[{"name":"Department of Network and Computer Security, College of Engineering, SUNY Polytechnic Institute, Utica, NY 13502, USA"},{"name":"Department of Electrical Engineering, Faculty of Engineering at Shoubra, Benha University, Cairo 11629, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8719-501X","authenticated-orcid":false,"given":"Mohamed","family":"Mahmoud","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Tennessee Tech University, Cookeville, TN 38505, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-8977","authenticated-orcid":false,"given":"Tariq","family":"Alshawi","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, College of Engineering, King Saud University, Riyadh 11421, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8000-4161","authenticated-orcid":false,"given":"Mohamed I.","family":"Ibrahem","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Faculty of Engineering at Shoubra, Benha University, Cairo 11629, Egypt"},{"name":"Department of Cyber Systems Engineering, Augusta University, Augusta, GA 30912, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1892","DOI":"10.1109\/TEM.2025.3563779","article-title":"Enabling System Flexibility in Smart Grid Architecture","volume":"72","author":"Ayad","year":"2025","journal-title":"IEEE Trans. Eng. Manag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1055","DOI":"10.1109\/TIA.2024.3477447","article-title":"Solid-State Power Substations for Future Power Grids","volume":"61","author":"Mandal","year":"2025","journal-title":"IEEE Trans. Ind. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1950057","DOI":"10.1142\/S0218126619500579","article-title":"Optimal energy management strategy and novel control approach for DPGSs under unbalanced grid faults","volume":"28","author":"Abbassi","year":"2019","journal-title":"J. Circuits Syst. Comput."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1109\/TPWRD.2005.855444","article-title":"Power quality indices for transient disturbances","volume":"21","author":"Shin","year":"2006","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1109\/61.871378","article-title":"A direction finder for power quality disturbances based upon disturbance power and energy","volume":"15","author":"Parsons","year":"2000","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"6711","DOI":"10.1002\/er.7611","article-title":"Improved off-grid wind\/photovoltaic\/hybrid energy storage system based on new framework of moth-flame optimization algorithm","volume":"46","author":"Abbassi","year":"2022","journal-title":"Int. J. Energy Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1309","DOI":"10.1007\/s12555-014-0264-4","article-title":"Quality improvement of shunt active power filter with direct instantaneous power estimator based on Virtual Flux","volume":"14","author":"Saidi","year":"2016","journal-title":"Int. J. Control. Autom. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1504\/IJSPM.2016.077339","article-title":"Solar photovoltaic energy system-based shunt active filter for electrical energy quality improvement","volume":"11","author":"Saidi","year":"2016","journal-title":"Int. J. Simul. Process Model."},{"key":"ref_9","first-page":"1","article-title":"Deep Fractional Multidimensional Spectrum Convolutional Neural Fusion Network for Identifying Complex Power Quality Disturbance","volume":"73","author":"He","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"86434","DOI":"10.1109\/ACCESS.2024.3416684","article-title":"High-Precision Intelligent Identification of Complex Power Quality Disturbances Based on Improved KST and CNNs","volume":"12","author":"Bai","year":"2024","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"124789","DOI":"10.1016\/j.apenergy.2024.124789","article-title":"A privacy-preserving heterogeneous federated learning framework with class imbalance learning for electricity theft detection","volume":"378","author":"Wen","year":"2025","journal-title":"Appl. Energy"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1109\/JSYST.2025.3581524","article-title":"Federated Learning-Based Distributed Localization of False Data Injection Attacks on Smart Grids","volume":"19","author":"Davis","year":"2025","journal-title":"IEEE Syst. J."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Rahman, R., Kumar, N., and Nguyen, D.C. (2025, January 10\u201313). Electrical load forecasting in smart grid: A personalized federated learning approach. Proceedings of the 2025 IEEE 22nd Consumer Communications & Networking Conference (CCNC), Las Vegas, NV, USA.","DOI":"10.1109\/CCNC54725.2025.10976072"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hasan, M.K., Kabir, S.R., Islam, S., Abdullah, S., Khan, M.A., Brahim, G.B., Li, Y., and Abbas, H.S. (IEEE Commun. Stand. Mag., 2025). Edge Smart Meter Based LSTM Federated Learning with AES Cryptographic Blockchain for Smart Grid AIoT Networks, IEEE Commun. Stand. Mag., early access.","DOI":"10.1109\/MCOMSTD.2025.3575512"},{"key":"ref_15","first-page":"103993","article-title":"IDS-DWKAFL: An intrusion detection scheme based on Dynamic Weighted K-asynchronous Federated Learning for smart grid","volume":"89","author":"Wen","year":"2025","journal-title":"J. Inf. Secur. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2519912","DOI":"10.1109\/TIM.2022.3214284","article-title":"Detection and Classification of Multiple Power Quality Disturbances Using Stockwell Transform and Deep Learning","volume":"71","author":"Cui","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ucar, F., Alcin, O.F., Dandil, B., and Ata, F. (2018). Power quality event detection using a fast extreme learning machine. Energies, 11.","DOI":"10.3390\/en11010145"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/s42835-022-01177-1","article-title":"Deep Learning Based a New Approach for Power Quality Disturbances Classification in Power Transmission System","volume":"18","author":"Topaloglu","year":"2023","journal-title":"J. Electr. Eng. Technol."},{"key":"ref_19","first-page":"7917500","article-title":"Automatic detection of power quality disturbance using convolutional neural network structure with gated recurrent unit","volume":"2021","author":"Singh","year":"2021","journal-title":"Mob. Inf. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"108695","DOI":"10.1016\/j.epsr.2022.108695","article-title":"Ensemble deep learning for automated classification of power quality disturbances signals","volume":"213","author":"Wang","year":"2022","journal-title":"Electr. Power Syst. Res."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"890","DOI":"10.1109\/ACCESS.2022.3233767","article-title":"Classification of Power Quality Disturbance Using Segmented and Modified S-Transform and DCNN-MSVM Hybrid Model","volume":"11","author":"Liu","year":"2023","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tan, Y., and Deka, D. (2018, January 29\u201331). Is Machine Learning in Power Systems Vulnerable?. Proceedings of the 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Aalborg, Denmark.","DOI":"10.1109\/SmartGridComm.2018.8587547"},{"key":"ref_23","unstructured":"Goodfellow, I.J., Shlens, J., and Szegedy, C. (2014). Explaining and harnessing adversarial examples. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"11038","DOI":"10.1109\/JIOT.2023.3243086","article-title":"A Novel Evasion Attack Against Global Electricity Theft Detectors and a Countermeasure","volume":"10","author":"Badr","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3962","DOI":"10.1109\/TNSE.2025.3567340","article-title":"Trojan Attack and Defense for Deep Learning based Power Quality Disturbances Classification","volume":"12","author":"Khan","year":"2025","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ning, R., Xin, C., and Wu, H. (2022, January 2\u20135). TrojanFlow: A Neural Backdoor Attack to Deep Learning-based Network Traffic Classifiers. Proceedings of the IEEE INFOCOM 2022\u2014IEEE Conference on Computer Communications, London, UK.","DOI":"10.1109\/INFOCOM48880.2022.9796878"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Ma, X., Erfani, S.M., and Bailey, J. (2023, January 8\u201310). Backdoor Attacks on Time Series: A Generative Approach. Proceedings of the 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), Raleigh, NC, USA.","DOI":"10.1109\/SaTML54575.2023.00034"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ding, D., Zhang, M., Huang, Y., Pan, X., Feng, F., Jiang, E., and Yang, M. (2022, January 9\u201312). Towards Backdoor Attack on Deep Learning based Time Series Classification. Proceedings of the 2022 IEEE 38th International Conference on Data Engineering (ICDE), Kuala Lumpur, Malaysia.","DOI":"10.1109\/ICDE53745.2022.00100"},{"key":"ref_29","unstructured":"Nguyen, T.D., Rieger, P., Chen, H., Yalame, H., M\u00f6llering, H., Fereidooni, H., Marchal, S., Miettinen, M., Mirhoseini, A., and Zeitouni, S. (2022, January 10\u201312). FLAME: Taming Backdoors in Federated Learning. Proceedings of the 31st USENIX Security Symposium (USENIX Security 22), Boston, MA, USA."},{"key":"ref_30","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent. Proceedings of the Advances in Neural Information Processing Systems."},{"key":"ref_31","unstructured":"Colosimo, F., and De Rango, F. (November, January 30). Median-Krum: A Joint Distance-Statistical Based Byzantine-Robust Algorithm in Federated Learning. Proceedings of the Int\u2019l ACM Symposium on Mobility Management and Wireless Access, Montreal, QC, Canada. MobiWac \u201923."},{"key":"ref_32","unstructured":"Fung, C., Yoon, C.J.M., and Beschastnikh, I. (2020). Mitigating Sybils in Federated Learning Poisoning. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"10708","DOI":"10.1109\/ACCESS.2023.3238823","article-title":"Poisoning Attacks in Federated Learning: A Survey","volume":"11","author":"Xia","year":"2023","journal-title":"IEEE Access"},{"key":"ref_34","first-page":"191828","article-title":"A Trojan Attack Against Smart Grid Federated Learning and Countermeasures","volume":"12","author":"Bondok","year":"2024","journal-title":"IEEE Access"},{"key":"ref_35","unstructured":"(2019). IEEE Recommended Practice for Monitoring Electric Power Quality. Institute of Electrical and Electronics Engineers (Standard No. IEEE Standard 1159-2019)."},{"key":"ref_36","unstructured":"Kaggle (2025, October 15). SEED\u2014Power Quality Disturbance Dataset. Available online: https:\/\/www.kaggle.com\/datasets\/sumairaziz\/seed-power-quality-disturbance-dataset."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"112889","DOI":"10.1016\/j.measurement.2023.112889","article-title":"XPQRS: Expert power quality recognition system for sensitive load applications","volume":"216","author":"Khan","year":"2023","journal-title":"Measurement"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Mbow, M., Takahashi, T., and Sakurai, K. (2024, January 26\u201329). Poisoning Attacks on Federated-learning based NIDS. Proceedings of the 2024 Twelfth International Symposium on Computing and Networking Workshops (CANDARW), Naha, Japan.","DOI":"10.1109\/CANDARW64572.2024.00020"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"181071","DOI":"10.1109\/ACCESS.2025.3621608","article-title":"Efficient XAI-based Federated Learning Approach for Accurate Detection of False Data in Smart Grid","volume":"13","author":"Elgarhy","year":"2025","journal-title":"IEEE Access"},{"key":"ref_40","first-page":"13","article-title":"Federated learning enabled ids for internet of things on non-IID data","volume":"24","author":"Elnakib","year":"2024","journal-title":"Int. J. Intell. Comput. Inf. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TIFS.2024.3516555","article-title":"Federated Learning Minimal Model Replacement Attack Using Optimal Transport: An Attacker Perspective","volume":"20","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"112953","DOI":"10.1109\/ACCESS.2023.3323617","article-title":"Novel Evasion Attacks against Adversarial Training Defense for Smart Grid Federated Learning","volume":"11","author":"Bondok","year":"2023","journal-title":"IEEE Access"},{"key":"ref_43","unstructured":"Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., and Shmatikov, V. (2020, January 26\u201328). How to Backdoor Federated Learning. Proceedings of the International Conference on Artificial Intelligence and Statistics, Online."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"166","DOI":"10.3390\/jcp3020010","article-title":"Cybersecurity for AI systems: A survey","volume":"3","author":"Sangwan","year":"2023","journal-title":"J. Cybersecur. Priv."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"4574","DOI":"10.1109\/TIFS.2021.3108434","article-title":"Privacy-enhanced federated learning against poisoning adversaries","volume":"16","author":"Liu","year":"2021","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"45288","DOI":"10.1109\/JIOT.2025.3599106","article-title":"Securing Smart Grid Federated Learning Against Advanced Evasion Attacks Using Ensemble-Based Adversarial Training","volume":"12","author":"Bondok","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"ref_47","first-page":"1364","article-title":"Privacy-preserving federated deep learning with irregular users","volume":"19","author":"Xu","year":"2020","journal-title":"IEEE Trans. Dependable Secur. Comput."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6880\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T05:27:48Z","timestamp":1763011668000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/22\/6880"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":47,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["s25226880"],"URL":"https:\/\/doi.org\/10.3390\/s25226880","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]}}}