{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:05:39Z","timestamp":1784300739892,"version":"3.55.0"},"reference-count":57,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hainan Provincial Natural Science Foundation of China","award":["625MS081"],"award-info":[{"award-number":["625MS081"]}]},{"name":"Hainan Provincial Natural Science Foundation of China","award":["2025-008"],"award-info":[{"award-number":["2025-008"]}]},{"name":"Haikou Science and Technology Special Fund","award":["625MS081"],"award-info":[{"award-number":["625MS081"]}]},{"name":"Haikou Science and Technology Special Fund","award":["2025-008"],"award-info":[{"award-number":["2025-008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Informatics"],"abstract":"<jats:p>Traditional spam detection methodologies often neglect user privacy preservation, potentially incurring data leakage risks. Furthermore, current federated learning models for spam detection face several critical challenges: (1) data heterogeneity and instability during server-side parameter aggregation, (2) training instability in single neural network architectures leading to mode collapse, and (3) constrained expressive capability in multi-module frameworks due to excessive complexity. These issues represent fundamental research pain points in federated learning-based spam detection systems. To address this technical challenge, this study innovatively integrates federated learning frameworks with multi-feature fusion techniques to propose a novel spam detection model, FPW-BC. The FPW-BC model addresses data distribution imbalance through the FedProx aggregation algorithm and enhances stability during server-side parameter aggregation via a horse-racing selection strategy. The model effectively mitigates limitations inherent in both single and multi-module architectures through hierarchical multi-feature fusion. To validate FPW-BC\u2019s performance, comprehensive experiments were conducted on six benchmark datasets with distinct distribution characteristics: CEAS, Enron, Ling, Phishing_email, Spam_email, and Fake_phishing, with comparative analysis against multiple baseline methods. Experimental results demonstrate that FPW-BC achieves exceptional generalization capability for various spam patterns while maintaining user privacy preservation. The model attained 99.40% accuracy on CEAS and 99.78% on Fake_phishing, representing significant dual improvements in both privacy protection and detection efficiency.<\/jats:p>","DOI":"10.3390\/informatics12030093","type":"journal-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T12:34:03Z","timestamp":1757680443000},"page":"93","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Federated Learning Spam Detection Based on FedProx and Multi-Level Multi-Feature Fusion"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4871-5594","authenticated-orcid":false,"given":"Yunpeng","family":"Xiong","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Hainan Normal University, Haikou 571158, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8689-6626","authenticated-orcid":false,"given":"Junkuo","family":"Cao","sequence":"additional","affiliation":[{"name":"Information Network and Data Center, Hainan Normal University, Haikou 571158, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guolian","family":"Chen","sequence":"additional","affiliation":[{"name":"State-Owned Assets Management Office, Hainan Normal University, Haikou 571158, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"ref_1","first-page":"5130","article-title":"Email spam filtering technique: Challenges and solutions","volume":"101","author":"Yasin","year":"2023","journal-title":"J. Theor. Appl. Inf. Technol."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Altulaihan, E., Alismail, A., Hafizur Rahman, M., and Ibrahim, A.A. (2023). Email security issues, tools, and techniques used in investigation. Sustainability, 15.","DOI":"10.3390\/su151310612"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"103600","DOI":"10.1016\/j.cose.2023.103600","article-title":"A comprehensive examination of email spoofing: Issues and prospects for email security","volume":"137","author":"Sethuraman","year":"2024","journal-title":"Comput. Secur."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103671","DOI":"10.1016\/j.cose.2023.103671","article-title":"The human factor in phishing: Collecting and analyzing user behavior when reading emails","volume":"139","author":"Gallo","year":"2024","journal-title":"Comput. Secur."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"102937","DOI":"10.1016\/j.cose.2022.102937","article-title":"Why people keep falling for phishing scams: The effects of time pressure and deception cues on the detection of phishing emails","volume":"123","author":"Butavicius","year":"2022","journal-title":"Comput. Secur."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"103695","DOI":"10.1016\/j.cose.2023.103695","article-title":"Exploring the evidence for email phishing training: A scoping review","volume":"139","author":"Marshall","year":"2024","journal-title":"Comput. Secur."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1007\/978-981-16-3945-6_67","article-title":"Designing an email security awareness program for state-owned enterprises in namibia","volume":"Volume 2","author":"Morolong","year":"2022","journal-title":"IOT with Smart Systems: Proceedings of ICTIS 2021"},{"key":"ref_8","first-page":"808","article-title":"Security awareness strategy for Phishing email scams: A Case Study one of a company in Singapore","volume":"7","author":"Febriyani","year":"2023","journal-title":"JOIV Int. J. Inform. Vis."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3043","DOI":"10.1007\/s40747-022-00760-3","article-title":"Cloud-based email phishing attack using machine and deep learning algorithm","volume":"9","author":"Butt","year":"2023","journal-title":"Complex Intell. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"65703","DOI":"10.1109\/ACCESS.2022.3183083","article-title":"A systematic literature review on phishing email detection using natural language processing techniques","volume":"10","author":"Salloum","year":"2022","journal-title":"IEEE Access"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"143627","DOI":"10.1109\/ACCESS.2024.3467996","article-title":"Email Spam: A Comprehensive Review of Optimize Detection Methods, Challenges, and Open Research Problems","volume":"12","author":"Tusher","year":"2024","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1007\/s10462-022-10195-4","article-title":"A review of spam email detection: Analysis of spammer strategies and the dataset shift problem","volume":"56","author":"Fidalgo","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Dharrao, D., Gaikwad, P., Singh, A., Savita, A., Dharrao, M., and Bongale, A. (2023, January 26\u201327). Effective Email Filtering: A Machine Learning Approach to Distinguish Safe and Phishing Emails with SVM. Proceedings of the International Conference on Recent Innovations in Computing, Jammu, India.","DOI":"10.1007\/978-981-97-7862-1_12"},{"key":"ref_14","first-page":"25","article-title":"Sentence level analysis model for phishing detection using knn","volume":"6","author":"Sawe","year":"2024","journal-title":"J. Cybersecur."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1862888","DOI":"10.1155\/2022\/1862888","article-title":"Machine learning techniques for spam detection in email and IoT platforms: Analysis and research challenges","volume":"2022","author":"Ahmed","year":"2022","journal-title":"Secur. Commun. Netw."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Thakur, K., Ali, M.L., Obaidat, M.A., and Kamruzzaman, A. (2023). A systematic review on deep-learning-based phishing email detection. Electronics, 12.","DOI":"10.3390\/electronics12214545"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1109\/TBDATA.2020.2978915","article-title":"LSTM based phishing detection for big email data","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Trans. Big Data"},{"key":"ref_18","first-page":"88","article-title":"Deteksi Email Spam menggunakan Algoritma Convolutional Neural Network (CNN)","volume":"10","author":"Bachri","year":"2024","journal-title":"JEPIN (J. Edukasi Dan Penelit. Inform.)"},{"key":"ref_19","first-page":"4315","article-title":"GRUSpam: Robust e-mail spam detection using gated recurrent unit (GRU) algorithm","volume":"15","author":"Wanda","year":"2023","journal-title":"Int. J. Inf. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.neucom.2019.08.095","article-title":"Hybrid neural networks for big data classification","volume":"390","author":"Zamora","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"103378","DOI":"10.1016\/j.cose.2023.103378","article-title":"A comprehensive dual-layer architecture for phishing and spam email detection","volume":"133","author":"Doshi","year":"2023","journal-title":"Comput. Secur."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"103545","DOI":"10.1016\/j.jnca.2022.103545","article-title":"Helphed: Hybrid ensemble learning phishing email detection","volume":"210","author":"Bountakas","year":"2023","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"120977","DOI":"10.1016\/j.eswa.2023.120977","article-title":"Email spam detection using hierarchical attention hybrid deep learning method","volume":"233","author":"Zavrak","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"110226","DOI":"10.1016\/j.asoc.2023.110226","article-title":"Classifying spam emails using agglomerative hierarchical clustering and a topic-based approach","volume":"139","author":"Fidalgo","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"100473","DOI":"10.1016\/j.eij.2024.100473","article-title":"Email spam detection by deep learning models using novel feature selection technique and BERT","volume":"26","author":"Nasreen","year":"2024","journal-title":"Egypt. Inform. J."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Uddin, M.A., and Sarker, I.H. (2024). An Explainable Transformer-based Model for Phishing Email Detection: A Large Language Model Approach. arXiv.","DOI":"10.2139\/ssrn.4785953"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"42131","DOI":"10.1109\/ACCESS.2024.3375882","article-title":"Devising and Detecting Phishing Emails Using Large Language Models","volume":"12","author":"Heiding","year":"2024","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"26545","DOI":"10.1007\/s11042-023-14814-2","article-title":"Detecting ham and spam emails using feature union and supervised machine learning models","volume":"82","author":"Rustam","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"11968","DOI":"10.3390\/app112411968","article-title":"MMPC-RF: A deep multimodal feature-level fusion architecture for hybrid spam E-mail detection","volume":"11","author":"Hnini","year":"2021","journal-title":"Appl. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"107525","DOI":"10.1016\/j.knosys.2021.107525","article-title":"AMFF: A new attention-based multi-feature fusion method for intention recognition","volume":"233","author":"Liu","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"76","DOI":"10.7763\/IJCTE.2023.V15.1334","article-title":"A late multi-modal fusion model for detecting hybrid spam e-mail","volume":"15","author":"Zhang","year":"2023","journal-title":"Int. J. Comput. Theory Eng."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"118459","DOI":"10.1016\/j.eswa.2022.118459","article-title":"Sequence neural network for recommendation with multi-feature fusion","volume":"210","author":"Gu","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.neucom.2022.06.031","article-title":"Multi-feature fusion: Graph neural network and CNN combining for hyperspectral image classification","volume":"501","author":"Ding","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1186\/s40537-022-00566-7","article-title":"Social network data analysis to highlight privacy threats in sharing data","volume":"9","author":"Cerruto","year":"2022","journal-title":"J. Big Data"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"106775","DOI":"10.1016\/j.knosys.2021.106775","article-title":"A survey on federated learning","volume":"216","author":"Zhang","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"106854","DOI":"10.1016\/j.cie.2020.106854","article-title":"A review of applications in federated learning","volume":"149","author":"Li","year":"2020","journal-title":"Comput. Ind. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3460427","article-title":"A comprehensive survey of privacy-preserving federated learning: A taxonomy, review, and future directions","volume":"54","author":"Yin","year":"2021","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1016\/j.future.2020.10.007","article-title":"A survey on security and privacy of federated learning","volume":"115","author":"Mothukuri","year":"2021","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"103061","DOI":"10.1016\/j.ipm.2022.103061","article-title":"Federated learning review: Fundamentals, enabling technologies, and future applications","volume":"59","author":"Banabilah","year":"2022","journal-title":"Inf. Process. Manag."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3570953","article-title":"Blockchain-empowered federated learning: Challenges, solutions, and future directions","volume":"55","author":"Zhu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3453476","article-title":"Federated learning for smart healthcare: A survey","volume":"55","author":"Nguyen","year":"2022","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.future.2023.02.021","article-title":"Review on security of federated learning and its application in healthcare","volume":"144","author":"Li","year":"2023","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"110424","DOI":"10.1016\/j.patcog.2024.110424","article-title":"Federated learning for medical image analysis: A survey","volume":"151","author":"Guan","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"102189","DOI":"10.1016\/j.inffus.2023.102189","article-title":"Federated learning for IoT devices: Enhancing TinyML with on-board training","volume":"104","author":"Ficco","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"2966","DOI":"10.1109\/TNSE.2022.3178970","article-title":"Communication-efficient and cross-chain empowered federated learning for artificial intelligence of things","volume":"9","author":"Kang","year":"2022","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Sun, Y., Chong, N., and Ochiai, H. (2022, January 9\u201312). Federated phish bowl: Lstm-based decentralized phishing email detection. Proceedings of the 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Prague, Czech Republic.","DOI":"10.1109\/SMC53654.2022.9945584"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Ul Haq, I., Black, P., Gondal, I., Kamruzzaman, J., Watters, P., and Kayes, A. (2022, January 18\u201320). Spam email categorization with nlp and using federated deep learning. Proceedings of the International Conference on Advanced Data Mining and Applications, Brisbane, QLD, Australia.","DOI":"10.1007\/978-3-031-22137-8_2"},{"key":"ref_48","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref_49","first-page":"1","article-title":"A non-parametric view of FedAvg and FedProx: Beyond stationary points","volume":"24","author":"Su","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref_50","first-page":"5901","article-title":"Intelligent Deep Learning Based Cybersecurity Phishing Email Detection and Classification","volume":"74","author":"Brindha","year":"2023","journal-title":"Comput. Mater. Contin."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"41","DOI":"10.59324\/ejaset.2025.3(2).04","article-title":"Building an Intelligent Phishing Email Detection System Using Machine Learning and Feature Engineering","volume":"3","author":"Chinta","year":"2025","journal-title":"Eur. J. Appl. Sci. Eng. Technol."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Thapa, C., Tang, J.W., Abuadbba, A., Gao, Y., Camtepe, S., Nepal, S., Almashor, M., and Zheng, Y. (2023). Evaluation of federated learning in phishing email detection. Sensors, 23.","DOI":"10.3390\/s23094346"},{"key":"ref_53","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2\u20137). Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"6515","DOI":"10.1007\/s00521-024-10969-7","article-title":"Fairness-driven federated learning-based spam email detection using clustering techniques","volume":"37","author":"Kaushal","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Ven\u010dkauskas, A., Toldinas, J., Morkevi\u010dius, N., Serkovas, E., and Kri\u0161taponis, M. (2025). Enhancing the Resilience of a Federated Learning Global Model Using Client Model Benchmark Validation. Electronics, 14.","DOI":"10.3390\/electronics14061215"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Anh, H.Q., Anh, P.T., Nguyen, P.S., and Hung, P.D. (2024, January 20\u201322). Federated Learning for Vietnamese SMS Spam Detection Using Pre-trained PhoBERT. Proceedings of the International Conference on Intelligent Data Engineering and Automated Learning, Valencia, Spain.","DOI":"10.1007\/978-3-031-77731-8_24"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1017\/S1351324916000334","article-title":"Word2Vec","volume":"23","author":"Church","year":"2017","journal-title":"Nat. Lang. Eng."}],"container-title":["Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2227-9709\/12\/3\/93\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:44:39Z","timestamp":1760035479000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2227-9709\/12\/3\/93"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"references-count":57,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["informatics12030093"],"URL":"https:\/\/doi.org\/10.3390\/informatics12030093","relation":{},"ISSN":["2227-9709"],"issn-type":[{"value":"2227-9709","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,12]]}}}