{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T22:21:31Z","timestamp":1790893291952,"version":"4.1.0"},"reference-count":48,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"\n The proliferation of Internet of Medical Things (IoMT) devices has created critical cybersecurity challenges demanding intrusion detection systems that achieve high accuracy across diverse attack taxonomies while preserving patient privacy across institutional boundaries. Existing federated learning (FL) approaches face an inherent tension: Transformer-based architectures achieve strong detection performance but incur quadratic computational complexity and substantial communication overhead, while lightweight classifiers sacrifice representational capacity. Moreover, most FL-based intrusion detection systems lack formal privacy guarantees and robustness against adversarial participants. This paper introduces FedMamba-IoMT, the first federated State Space Model framework for privacy-preserving intrusion detection in IoMT networks, incorporating differential privacy (DP-SGD), Byzantine-resilient aggregation, and multi-level explainability. The proposed architecture reformulates tabular network traffic features as pseudo-sequential tokens processed through stacked selective State Space Model (Mamba) blocks with gated residual connections, achieving linear computational complexity\n \n \n \n \n \n \ud835\udcaa<\/mml:mi>\n (<\/mml:mo>\n n<\/mml:mi>\n )<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n with 78% fewer parameters than Transformer alternatives. We design a novel FedMamba aggregation strategy that weights client contributions by a convex combination of dataset proportion and inverse validation loss, augmented with a cosine similarity-based Byzantine filter that detects and excludes malicious model updates. Integration of DP-SGD with R\u00e9nyi differential privacy accounting provides formal privacy guarantees (\n \n \n \n \n \n \u03b5<\/mml:mi>\n \u2208<\/mml:mo>\n {<\/mml:mo>\n 1.0<\/mml:mn>\n ,<\/mml:mo>\n 2.0<\/mml:mn>\n ,<\/mml:mo>\n 3.0<\/mml:mn>\n ,<\/mml:mo>\n 5.0<\/mml:mn>\n ,<\/mml:mo>\n 8.0<\/mml:mn>\n }<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n ,\n \n \n \n \n \n \u03b4<\/mml:mi>\n =<\/mml:mo>\n \n 10<\/mml:mn>\n \n \u2212<\/mml:mo>\n 5<\/mml:mn>\n <\/mml:mrow>\n <\/mml:msup>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n ) while maintaining competitive accuracy. Comprehensive evaluation across three benchmark datasets\u2014Edge-IIoTset (2,219,201 samples, 15 classes), CICIoMT2024 (3,204,537 samples, 19 classes), and Gotham Dataset 2025 (496,191 samples, 8 high-level traffic categories)\u2014demonstrates that FedMamba-IoMT achieves\n \n \n \n \n \n 99.47<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.04<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n %,\n \n \n \n \n \n 99.52<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.04<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n %, and\n \n \n \n \n \n 98.90<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.04<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n % multiclass accuracy without DP, and 98.52%, 98.18%, and 97.16% at\n \n \n \n \n \n \u03b5<\/mml:mi>\n =<\/mml:mo>\n 3.0<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n , surpassing all prior federated IDS approaches. Byzantine resilience experiments demonstrate that the proposed defense maintains >95% accuracy under 30% malicious clients across label-flipping, model poisoning, and free-rider attacks. Gradient inversion analysis confirms that FedMamba\u2019s compact parameterization (135K parameters, 0.52 MB) provides\n \n \n \n \n \n 2<\/mml:mn>\n \u00d7<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n higher reconstruction error compared to Transformer-based FL, and the integrated SHAP and LIME explainability framework supports regulatory compliance with the FDA\u2019s 2023 cybersecurity guidance for medical devices.\n <\/jats:p>","DOI":"10.1371\/journal.pone.0355601","type":"journal-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T17:31:09Z","timestamp":1786383069000},"page":"e0355601","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["FedMamba-IoMT: Federated state space models with differential privacy and byzantine resilience for privacy-preserving intrusion detection in Internet of Medical Things"],"prefix":"10.1371","volume":"21","author":[{"given":"Yasser Mohammad","family":"Al-Sharo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7622-5991","authenticated-orcid":true,"given":"Mohammed","family":"Tawfik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali Mansour","family":"Almadani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amr H.","family":"Abdelhaliem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Islam S.","family":"Fathi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7390-1964","authenticated-orcid":true,"given":"Gaber","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,10]]},"reference":[{"key":"pone.0355601.ref001","doi-asserted-by":"crossref","unstructured":"Al-Zidi NM, Tawfik M, Al-Hejri AM, Fathail I, Aldhaheri TA, Al-Tashi Q. Smart system for real-time remote patient monitoring based on Internet of Things. In: 2021 2nd International Conference on Computational Methods in Science & Technology (ICCMST). 2021. p. 1\u20136. https:\/\/doi.org\/10.1109\/iccmst54943.2021.00013","DOI":"10.1109\/ICCMST54943.2021.00013"},{"issue":"5","key":"pone.0355601.ref002","doi-asserted-by":"crossref","DOI":"10.1111\/exsy.70010","article-title":"A survey on Internet of Medical Things (IoMT): enabling technologies, security and explainability issues, challenges, and future directions","volume":"42","author":"MM Ozcelik","year":"2025","journal-title":"Expert Systems"},{"issue":"5","key":"pone.0355601.ref003","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2025.10180","article-title":"Ransomware attacks and data breaches in US Health Care Systems","volume":"8","author":"JX Jiang","year":"2025","journal-title":"JAMA Netw Open"},{"key":"pone.0355601.ref004","doi-asserted-by":"crossref","DOI":"10.2196\/46904","article-title":"Vulnerability to cyberattacks and sociotechnical solutions for health care systems: systematic review","volume":"26","author":"P Ewoh","year":"2024","journal-title":"J Med Internet Res"},{"key":"pone.0355601.ref005","unstructured":"U S Food and Drug Administration. Cybersecurity in medical devices: Quality system considerations and content of premarket submissions. FR 66458. 2023."},{"key":"pone.0355601.ref006","doi-asserted-by":"crossref","first-page":"4745","DOI":"10.1109\/ACCESS.2023.3349287","article-title":"A survey of deep learning technologies for intrusion detection in Internet of Things","volume":"12","author":"H Liao","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0355601.ref007","doi-asserted-by":"crossref","unstructured":"Saif S, Das P, Biswas S, Khari M, Shanmuganathan V. HIIDS: Hybrid intelligent intrusion detection system empowered with machine learning and metaheuristic algorithms for application in IoT based healthcare. Microprocessors and Microsystems. 2022;104622. doi: 10.1016\/j.micpro.2022.104622","DOI":"10.1016\/j.micpro.2022.104622"},{"issue":"8","key":"pone.0355601.ref008","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0304082","article-title":"Optimized intrusion detection in IoT and fog computing using ensemble learning and advanced feature selection","volume":"19","author":"M Tawfik","year":"2024","journal-title":"PLoS One"},{"issue":"11","key":"pone.0355601.ref009","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0334528","article-title":"E-RespiNet: An LLM-ELECTRA driven triple-stream CNN with feature fusion for asthma classification","volume":"20","author":"M Tawfik","year":"2025","journal-title":"PLoS One"},{"issue":"7","key":"pone.0355601.ref010","doi-asserted-by":"crossref","first-page":"100974","DOI":"10.1016\/j.patter.2024.100974","article-title":"Privacy preservation for federated learning in health care","volume":"5","author":"S Pati","year":"2024","journal-title":"Patterns (N Y)"},{"key":"pone.0355601.ref011","unstructured":"McMahan HB, Moore E, Ramage D, Hampson S, Ag\u00fcera y Arcas B. Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS). PMLR; 2017. p. 1273\u201382."},{"issue":"2","key":"pone.0355601.ref012","doi-asserted-by":"crossref","first-page":"101419","DOI":"10.1016\/j.xcrm.2024.101419","article-title":"Federated machine learning in healthcare: a systematic review on clinical applications and technical architecture","volume":"5","author":"ZL Teo","year":"2024","journal-title":"Cell Rep Med"},{"key":"pone.0355601.ref013","doi-asserted-by":"crossref","first-page":"100742","DOI":"10.1016\/j.iot.2023.100742","article-title":"Communication and computation efficiency in federated learning: a survey","volume":"22","author":"ORA Almanifi","year":"2023","journal-title":"Internet of Things"},{"issue":"3","key":"pone.0355601.ref014","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3625558","article-title":"Heterogeneous federated learning: state-of-the-art and research challenges","volume":"56","author":"M Ye","year":"2023","journal-title":"ACM Comput Surv"},{"key":"pone.0355601.ref015","unstructured":"Zhu L, Liu Z, Han S. Deep leakage from gradients. In: Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS). 2019. p. 14774\u201384."},{"key":"pone.0355601.ref016","unstructured":"Blanchard P, El Mhamdi EM, Guerraoui R, Stainer J. Machine learning with adversaries: byzantine tolerant gradient descent. In: Proceedings of the 30th Conference on Neural Information Processing Systems (NeurIPS). 2017. p. 119\u201329."},{"key":"pone.0355601.ref017","unstructured":"Fang M, Cao X, Jia J, Gong N. Local model poisoning attacks to Byzantine-robust federated learning. In: Proceedings of the 29th USENIX Security Symposium. 2020. p. 1605\u201322."},{"key":"pone.0355601.ref018","unstructured":"Gu A, Dao T. Mamba: linear-time sequence modeling with selective state spaces. In: Proceedings of the 1st Conference on Language Modeling (COLM). 2024."},{"key":"pone.0355601.ref019","unstructured":"Zhu L, Liao B, Zhang Q, Wang X, Liu W, Wang X. Vision Mamba: efficient visual representation learning with bidirectional state space model. In: Proceedings of the 41st International Conference on Machine Learning (ICML). 2024. p. 62429\u201342."},{"key":"pone.0355601.ref020","doi-asserted-by":"crossref","unstructured":"Wang T, Xie X, Wang W, Wang C, Zhao Y, Cui Y. Netmamba: efficient network traffic classification via pre-training unidirectional mamba. In: 2024 IEEE 32nd International Conference on Network Protocols (ICNP). 2024. p. 1\u201311. https:\/\/doi.org\/10.1109\/icnp61940.2024.10858569","DOI":"10.1109\/ICNP61940.2024.10858569"},{"issue":"1","key":"pone.0355601.ref021","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1007\/s11277-023-10774-w","article-title":"DHOA-ANFIS: a hybrid technique to detect routing attacks in wireless body area network","volume":"133","author":"S Saif","year":"2023","journal-title":"Wireless Pers Commun"},{"key":"pone.0355601.ref022","doi-asserted-by":"crossref","first-page":"40281","DOI":"10.1109\/ACCESS.2022.3165809","article-title":"Edge-IIoTset: a new comprehensive realistic cyber security dataset of IoT and IIoT applications for centralized and federated learning","volume":"10","author":"MA Ferrag","year":"2022","journal-title":"IEEE Access"},{"issue":"4","key":"pone.0355601.ref023","first-page":"401","article-title":"Enhancing IoT intrusion detection using dimensionality reduction and deep learning","volume":"33","author":"A Sufyan","year":"2024","journal-title":"Information Security Journal: A Global Perspective"},{"issue":"3","key":"pone.0355601.ref024","doi-asserted-by":"crossref","DOI":"10.1007\/s42979-026-04805-z","article-title":"An enhanced approach for edge-based intrusion detection based on a hybrid deep learning model CNN-DNN","volume":"7","author":"AM Elshewey","year":"2026","journal-title":"SN Comput Sci"},{"key":"pone.0355601.ref025","doi-asserted-by":"crossref","first-page":"45762","DOI":"10.1109\/ACCESS.2024.3380816","article-title":"A self-attention-based deep convolutional neural networks for IIoT networks intrusion detection","volume":"12","author":"MS Alshehri","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0355601.ref026","doi-asserted-by":"crossref","first-page":"101351","DOI":"10.1016\/j.iot.2024.101351","article-title":"CICIoMT2024: a benchmark dataset for multi-protocol security assessment in IoMT","volume":"28","author":"S Dadkhah","year":"2024","journal-title":"Internet of Things"},{"issue":"3","key":"pone.0355601.ref027","doi-asserted-by":"crossref","first-page":"2185","DOI":"10.32604\/cmes.2024.056308","article-title":"Augmenting Internet of Medical Things security: deep ensemble integration and methodological fusion","volume":"141","author":"H Naeem","year":"2024","journal-title":"CMES"},{"key":"pone.0355601.ref028","doi-asserted-by":"crossref","first-page":"1524286","DOI":"10.3389\/fmed.2025.1524286","article-title":"A deep reinforcement learning-based robust intrusion detection system for securing IoMT Healthcare Networks","volume":"12","author":"JA Shaikh","year":"2025","journal-title":"Front Med (Lausanne)"},{"issue":"12","key":"pone.0355601.ref029","doi-asserted-by":"crossref","first-page":"3693","DOI":"10.3390\/s25123693","article-title":"X-FuseRLSTM: a cross-domain explainable intrusion detection framework in iot using the attention-guided dual-path feature fusion and residual LSTM","volume":"25","author":"A Alabbadi","year":"2025","journal-title":"Sensors (Basel)"},{"issue":"1","key":"pone.0355601.ref030","doi-asserted-by":"crossref","DOI":"10.1186\/s13677-025-00785-2","article-title":"A novel IoT threat detection using GWO feature selection and CNN-enhanced LightGBM","volume":"14","author":"T Abid","year":"2025","journal-title":"J Cloud Comp"},{"issue":"1","key":"pone.0355601.ref031","doi-asserted-by":"crossref","first-page":"317","DOI":"10.30526\/39.1.4222","article-title":"An intrusion detection for Internet of Medical Things based on deep learning techniques","volume":"39","author":"AE Mohammad","year":"2026","journal-title":"IHJPAS"},{"key":"pone.0355601.ref032","unstructured":"Belarbi O, Spyridopoulos T, Anthi E, Rana O, Carnelli P, Khan A. Gotham Dataset 2025: a reproducible large-scale IoT network dataset for intrusion detection and security research. 2025. https:\/\/arxiv.org\/abs\/2502.03134"},{"issue":"2","key":"pone.0355601.ref033","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1109\/JBHI.2022.3186250","article-title":"Dew-cloud-based hierarchical federated learning for intrusion detection in IoMT","volume":"27","author":"P Singh","year":"2023","journal-title":"IEEE J Biomed Health Inform"},{"issue":"14","key":"pone.0355601.ref034","doi-asserted-by":"crossref","first-page":"4591","DOI":"10.3390\/s24144591","article-title":"BFLIDS: blockchain-driven federated learning for intrusion detection in IoMT networks","volume":"24","author":"K Begum","year":"2024","journal-title":"Sensors (Basel)"},{"issue":"2","key":"pone.0355601.ref035","doi-asserted-by":"crossref","DOI":"10.14569\/IJACSA.2025.01602129","article-title":"Securing Internet of Medical Things: an advanced federated learning approach","volume":"16","author":"A Misbah","year":"2025","journal-title":"ijacsa"},{"issue":"1","key":"pone.0355601.ref036","doi-asserted-by":"crossref","first-page":"40050","DOI":"10.1038\/s41598-025-25107-z","article-title":"FedMedSecure: federated few-shot learning with cross-attention mechanisms and explainable AI for collaborative healthcare cybersecurity","volume":"15","author":"M Tawfik","year":"2025","journal-title":"Sci Rep"},{"issue":"2","key":"pone.0355601.ref037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3695998","article-title":"Toward enhancing privacy preservation of a federated learning cnn intrusion detection system in IoT: method and empirical study","volume":"34","author":"D Torre","year":"2025","journal-title":"ACM Trans Softw Eng Methodol"},{"issue":"5","key":"pone.0355601.ref038","doi-asserted-by":"crossref","first-page":"1592","DOI":"10.3390\/s26051592","article-title":"FedSMOTE-DP: privacy-aware federated ensemble learning for intrusion detection in IoMT networks","volume":"26","author":"T Alsolami","year":"2026","journal-title":"Sensors (Basel)"},{"issue":"1","key":"pone.0355601.ref039","doi-asserted-by":"crossref","first-page":"10","DOI":"10.3390\/s25010010","article-title":"FFL-IDS: a fog-enabled federated learning-based intrusion detection system to counter jamming and spoofing attacks for the Industrial Internet of Things","volume":"25","author":"T Rehman","year":"2024","journal-title":"Sensors (Basel)"},{"key":"pone.0355601.ref040","doi-asserted-by":"crossref","first-page":"111933","DOI":"10.1016\/j.comnet.2025.111933","article-title":"IDS\u2013GraphMamba: a Markov-enhanced graph Mamba framework for real-time intrusion detection in IoMT edge networks","volume":"275","author":"S Ben Atitallah","year":"2026","journal-title":"Computer Networks"},{"key":"pone.0355601.ref041","doi-asserted-by":"crossref","unstructured":"Onteddu AR, Reddy Bandhela R, Reddy Kundavaram R, Jagannaveen V. A CNN-transformer hybrid for precise object detection in UAV aerial imagery. In: 2025 IEEE 3rd Global Conference on Wireless Computing and Networking (GCWCN). 2025. p. 1\u20137. https:\/\/doi.org\/10.1109\/gcwcn66157.2025.11448412","DOI":"10.1109\/GCWCN66157.2025.11448412"},{"issue":"2","key":"pone.0355601.ref042","doi-asserted-by":"crossref","first-page":"4508","DOI":"10.1109\/TCE.2025.3544885","article-title":"A resource-efficient federated learning framework for intrusion detection in IoMT networks","volume":"71","author":"Md Fahim-Ul-Islam","year":"2025","journal-title":"IEEE Trans Consumer Electron"},{"key":"pone.0355601.ref043","doi-asserted-by":"crossref","unstructured":"Abadi M, Chu A, Goodfellow I, McMahan HB, Mironov I, Talwar K, et al. Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security. 2016. p. 308\u201318. https:\/\/doi.org\/10.1145\/2976749.2978318","DOI":"10.1145\/2976749.2978318"},{"key":"pone.0355601.ref044","doi-asserted-by":"crossref","unstructured":"Mironov I. R\u00e9nyi differential privacy. In: 2017 IEEE 30th Computer Security Foundations Symposium (CSF). 2017. p. 263\u201375. https:\/\/doi.org\/10.1109\/csf.2017.11","DOI":"10.1109\/CSF.2017.11"},{"key":"pone.0355601.ref045","doi-asserted-by":"crossref","unstructured":"Bonawitz K, Ivanov V, Kreuter B, Marcedone A, McMahan HB, Patel S, et al. Practical secure aggregation for privacy-preserving machine learning. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. 2017. p. 1175\u201391. https:\/\/doi.org\/10.1145\/3133956.3133982","DOI":"10.1145\/3133956.3133982"},{"key":"pone.0355601.ref046","unstructured":"Yin D, Chen Y, Kannan R, Bartlett P. Byzantine-robust distributed learning: towards optimal statistical rates. In: Proceedings of the 35th International Conference on Machine Learning (ICML). 2018. p. 5650\u20139."},{"key":"pone.0355601.ref047","unstructured":"Gorishniy Y, Rubachev I, Khrulkov V, Babenko A. Revisiting deep learning models for tabular data. In: Advances in Neural Information Processing Systems. 2021."},{"key":"pone.0355601.ref048","doi-asserted-by":"crossref","first-page":"56889","DOI":"10.1109\/ACCESS.2026.3682136","article-title":"Noise-aware quantum support vector regression under simulator-based NISQ approximation","volume":"14","author":"RR Kundavaram","year":"2026","journal-title":"IEEE Access"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0355601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T17:31:25Z","timestamp":1786383085000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0355601"}},"subtitle":[],"editor":[{"given":"Sohail","family":"Saif","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,10]]},"references-count":48,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,10]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0355601","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,10]]}}}