Intrusion Detection Based on Federated Context-Aware Embedded Deep Transfer Learning in Heterogeneous Networks

preprint OA: closed
Full text JSON View at publisher

Abstract

Abstract With the continuous advancement of the Internet of Everything paradigm, network intrusion detection systems (IDS) are confronted with multiple challenges in heterogeneous data sharing, integration, and security. To address these issues, this paper proposes a theoretical framework based on Word Embedded Federated Deep Transfer Learning (WE-FDTL) under the dual constraints of inconsistent data distribution and privacy preservation in heterogeneous network environments. The core innovation lies in establishing a latent vector-driven federated semantic aggregation mechanism to achieve cross-domain distributed representation alignment and knowledge fusion. At the representation learning level, a semantic space mapping model is constructed using contextual word embedding techniques to transform discrete heterogeneous network sequences into continuous dense vectors. This approach eliminates the need for explicit data standardization while preserving structural information in high-dimensional space and ensuring embedded privacy protection. For feature alignment, we propose a domain adaptation method based on latent space projection. By establishing latent space alignment constraints across participants, this method achieves cross-domain feature alignment and unified representation, while enabling effective adaptation of latent space matrices to mainstream deep learning models, thereby addressing the domain shift problem in heterogeneous federated transfer learning. At the federated optimization level, a semantically embedded federated aggregation mechanism is designed to facilitate global cross-domain knowledge sharing and integration through gradient transmission in latent vector space instead of raw data exchange. This framework ensures data privacy at terminal devices while maintaining effective knowledge fusion. In simulation experiments, six deep learning models were employed to evaluate multi-class classification performance across three scenarios: single-source domain deep learning, single-source domain federated deep learning, and cross-source domain WE-FDTL. Experimental results on the mixed NSL-KDD and UNSW-NB15 datasets demonstrate that WE-FDTL achieves a client-side training accuracy of 94.88% and a validation accuracy of 90.36%, confirming the theoretical effectiveness and practical advantages of the proposed IDS approach in heterogeneous network environments.
Full text 33,768 characters · extracted from preprint-html · click to expand
Intrusion Detection Based on Federated Context-Aware Embedded Deep Transfer Learning in Heterogeneous Networks | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Intrusion Detection Based on Federated Context-Aware Embedded Deep Transfer Learning in Heterogeneous Networks Di Chen, Xinpeng Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8272325/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract With the continuous advancement of the Internet of Everything paradigm, network intrusion detection systems (IDS) are confronted with multiple challenges in heterogeneous data sharing, integration, and security. To address these issues, this paper proposes a theoretical framework based on Word Embedded Federated Deep Transfer Learning (WE-FDTL) under the dual constraints of inconsistent data distribution and privacy preservation in heterogeneous network environments. The core innovation lies in establishing a latent vector-driven federated semantic aggregation mechanism to achieve cross-domain distributed representation alignment and knowledge fusion. At the representation learning level, a semantic space mapping model is constructed using contextual word embedding techniques to transform discrete heterogeneous network sequences into continuous dense vectors. This approach eliminates the need for explicit data standardization while preserving structural information in high-dimensional space and ensuring embedded privacy protection. For feature alignment, we propose a domain adaptation method based on latent space projection. By establishing latent space alignment constraints across participants, this method achieves cross-domain feature alignment and unified representation, while enabling effective adaptation of latent space matrices to mainstream deep learning models, thereby addressing the domain shift problem in heterogeneous federated transfer learning. At the federated optimization level, a semantically embedded federated aggregation mechanism is designed to facilitate global cross-domain knowledge sharing and integration through gradient transmission in latent vector space instead of raw data exchange. This framework ensures data privacy at terminal devices while maintaining effective knowledge fusion. In simulation experiments, six deep learning models were employed to evaluate multi-class classification performance across three scenarios: single-source domain deep learning, single-source domain federated deep learning, and cross-source domain WE-FDTL. Experimental results on the mixed NSL-KDD and UNSW-NB15 datasets demonstrate that WE-FDTL achieves a client-side training accuracy of 94.88% and a validation accuracy of 90.36%, confirming the theoretical effectiveness and practical advantages of the proposed IDS approach in heterogeneous network environments. Heterogeneous Fusion Deep Learning Word Embedding Federated Learning Intrusion Detection Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 20 May, 2026 Reviewers invited by journal 09 Dec, 2025 Editor assigned by journal 06 Dec, 2025 Submission checks completed at journal 05 Dec, 2025 First submitted to journal 03 Dec, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8272325","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":559088691,"identity":"44e1cabd-fe39-46e5-abe8-f72ddd5135db","order_by":0,"name":"Di Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0UlEQVRIiWNgGAWjYDACCSDmMbDhZ2BIAHGZidaSJtlAohaGwyRo4Z/dfOzBm4LzEgbHk589YKiwTmxgP3sAvyV3jqUbzjG4LWFw5pm5AcOZ9MQGnrwEvFoMJHLMpHkMbtcZ3Egwk2BsO5zYIMFjQEBL/jeglnMSBjfSv0kw/iNKSw4bUMsBoJYcoC0NRGiRuJFmJjnHIFlC8sybMomEY+nGbTw5+LXwz0h+JvHmj50E3/H0bRIfaqxl+9nP4NeCChKAmI0E9aNgFIyCUTAKcAAAJxNA2AIGdQ8AAAAASUVORK5CYII=","orcid":"","institution":"Fudan University","correspondingAuthor":true,"prefix":"","firstName":"Di","middleName":"","lastName":"Chen","suffix":""},{"id":559088692,"identity":"152d839e-df3f-4f90-b7f5-4724cfeea971","order_by":1,"name":"Xinpeng Zhang","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"prefix":"","firstName":"Xinpeng","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-12-03 16:33:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8272325/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8272325/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98225957,"identity":"a629cb8c-c20b-4f14-90fc-149a7d015783","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45062767,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/491b12da7d45466d40f52ef6.docx"},{"id":98225927,"identity":"0c683f28-dab2-4ead-a680-ecb9198f21ad","added_by":"auto","created_at":"2025-12-15 12:36:53","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5001,"visible":true,"origin":"","legend":"","description":"","filename":"fd6763aa9b734200971df1d84a50a117.json","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/fb132b907b20ac3a6bbc1630.json"},{"id":98225929,"identity":"e37f6bcc-01b7-4139-851d-f194083e5331","added_by":"auto","created_at":"2025-12-15 12:36:53","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":174583,"visible":true,"origin":"","legend":"","description":"","filename":"fd6763aa9b734200971df1d84a50a1171enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/20b1378643945813ab4b4e70.xml"},{"id":98432622,"identity":"865db90d-22e2-430c-8bb6-26e936ab9731","added_by":"auto","created_at":"2025-12-17 16:49:45","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":541437,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/416279441da09d8cf07e1cc3.jpeg"},{"id":98433850,"identity":"acf66417-d075-4e02-b367-ce0eb1199bdf","added_by":"auto","created_at":"2025-12-17 16:51:10","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":455252,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/194fbce07b46a2800ab24f16.jpeg"},{"id":98432035,"identity":"6a910e30-61bc-44c4-b247-02cd1cb39f6d","added_by":"auto","created_at":"2025-12-17 16:48:52","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1516532,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/8f11def9e4b87b3243656ce6.jpeg"},{"id":98225931,"identity":"f4e660d9-a5f1-498a-bcdb-e0076d3aa57b","added_by":"auto","created_at":"2025-12-15 12:36:53","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":273997,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/1348e82aba594504ac6e6c9a.jpeg"},{"id":98225932,"identity":"4356febd-fda6-4c0c-859a-a76847c7c3ec","added_by":"auto","created_at":"2025-12-15 12:36:53","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":188102,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage13.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/3f5ce135857da6c5c51d4df4.jpeg"},{"id":98432913,"identity":"8f6672f0-e298-4033-8020-651c3ee97f92","added_by":"auto","created_at":"2025-12-17 16:50:07","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":373903,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage14.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/efde4e6670accf006e0b7ddc.jpeg"},{"id":98225935,"identity":"54ee6078-e42a-4bef-b182-17c27e1ddce0","added_by":"auto","created_at":"2025-12-15 12:36:53","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":512418,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage15.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/cac72bbb95f28506c42b7983.jpeg"},{"id":98225937,"identity":"e4062a5c-b181-4ced-939f-343e6ab1725f","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"jpeg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14982,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage16.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/87e81a8cf3c7805373d815b3.jpeg"},{"id":98225941,"identity":"dbc25b04-4651-447c-85e3-3745819c82e2","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":140502,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage17.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/fe8fe4b18c0703f02fe91c0f.png"},{"id":98433852,"identity":"16c09cb1-bbb7-4fee-a2d6-9ca379dd1856","added_by":"auto","created_at":"2025-12-17 16:51:10","extension":"jpeg","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":467200,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/1b552b656bbaad8ea366f2c0.jpeg"},{"id":98225936,"identity":"2b3a4dfc-c86a-49c0-bdd8-58c3a895c828","added_by":"auto","created_at":"2025-12-15 12:36:53","extension":"jpeg","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":492817,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/ab04cb1cb5270e7cc61e47f5.jpeg"},{"id":98225943,"identity":"f28bd7bb-9220-4b61-bb98-cfcffa63cc15","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"jpeg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":729887,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/684ea3a73119bd04e9e9e9a6.jpeg"},{"id":98225948,"identity":"b2dc91d7-2805-40e9-b79f-3253f5f6b81f","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"jpeg","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":541661,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/122035c5e12ffc656fcf6d34.jpeg"},{"id":98225953,"identity":"984c8b0a-5428-4356-a895-4ae47823e8dd","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"jpeg","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":948810,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/63651e06f48c3a5b68d817ce.jpeg"},{"id":98433943,"identity":"32b366b7-29ef-4e72-bd1d-02cf20a3e8c6","added_by":"auto","created_at":"2025-12-17 16:51:16","extension":"jpeg","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":629882,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/de2a9b6e0e61590850d64f0f.jpeg"},{"id":98225946,"identity":"95a63d5b-95a5-4a77-bd6f-0e18d306d82c","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"jpeg","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1280369,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/62ac85710559087e871ce8db.jpeg"},{"id":98433813,"identity":"272be3b6-85fb-49e1-83c9-ab4b0f4677b1","added_by":"auto","created_at":"2025-12-17 16:51:08","extension":"jpeg","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":863909,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/1ebcb66578993f392ef10b47.jpeg"},{"id":98432763,"identity":"69ed4d8a-994f-485e-99d2-ee936ed0617f","added_by":"auto","created_at":"2025-12-17 16:49:55","extension":"wmf","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1024,"visible":true,"origin":"","legend":"","description":"","filename":"image5.wmf","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/c27e170d3dd0863a4c493113.wmf"},{"id":98225961,"identity":"08158bb1-177b-4873-ad93-e6dac64f081f","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"wmf","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1170,"visible":true,"origin":"","legend":"","description":"","filename":"image6.wmf","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/9ad162d7e141adbb4ae1cf80.wmf"},{"id":98432707,"identity":"7043924c-51f6-4e35-896f-9aa15e44daed","added_by":"auto","created_at":"2025-12-17 16:49:49","extension":"wmf","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":918,"visible":true,"origin":"","legend":"","description":"","filename":"image7.wmf","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/a1f7d88ae17dc7b3e0bffa52.wmf"},{"id":98432991,"identity":"e5cea2d0-b85a-4957-b573-9a3d9cf84b79","added_by":"auto","created_at":"2025-12-17 16:50:11","extension":"wmf","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1104,"visible":true,"origin":"","legend":"","description":"","filename":"image8.wmf","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/3cdaf2d422fb220193960435.wmf"},{"id":98225949,"identity":"909a33e8-688a-4b6f-9493-63babe055b02","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"wmf","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2126,"visible":true,"origin":"","legend":"","description":"","filename":"image9.wmf","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/c279e0a381d34d60a01ce1b9.wmf"},{"id":98431932,"identity":"83d708f8-57ae-40d1-987e-76b9157c900b","added_by":"auto","created_at":"2025-12-17 16:48:39","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":132870,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/af3694ead7c429410282be45.png"},{"id":98433899,"identity":"819a96ca-bc41-4583-9122-12ce17de4b6d","added_by":"auto","created_at":"2025-12-17 16:51:13","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":101277,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/f52c218fbcee3a408df0cd63.png"},{"id":98433324,"identity":"74204ea4-9339-487b-908f-46b4daa2c5d3","added_by":"auto","created_at":"2025-12-17 16:50:37","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":508383,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/222711ba5a72ed98fe1930aa.png"},{"id":98225955,"identity":"f0aefaf2-692e-4d64-bda0-4d8fe761fc46","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":74862,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/22ffb3a41ac4c6f95fc8bfa7.png"},{"id":98433321,"identity":"bd555b15-5522-491a-87c3-d18b400a3b2f","added_by":"auto","created_at":"2025-12-17 16:50:37","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45614,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/1c8b8a8d9210bb062fa90946.png"},{"id":98432988,"identity":"c1c281f5-bd80-46a9-94e3-220a7e47c238","added_by":"auto","created_at":"2025-12-17 16:50:11","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":95215,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/38c66cabf16dc44d5552a81c.png"},{"id":98225962,"identity":"7f90c093-9d0a-4004-9e46-d652c03341f7","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124271,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/951a11cf5b75840cc1efe246.png"},{"id":98225951,"identity":"5ad0e4ce-89d3-459c-bb38-4d283a1d1c45","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30791,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/d9c4d6a4c7d3cb3391950334.png"},{"id":98225958,"identity":"cdbe3468-fb79-4062-9ff2-6f08924dd1a3","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12524,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage17.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/48effa909d61e00df6e10489.png"},{"id":98434040,"identity":"ceb7c4d4-5d28-4db2-8cf3-c151a18dd94e","added_by":"auto","created_at":"2025-12-17 16:51:26","extension":"png","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":126925,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/5cbf3edd6bc55afbe31c762d.png"},{"id":98434052,"identity":"993b699e-41c2-48f7-869f-47a057acb7b0","added_by":"auto","created_at":"2025-12-17 16:51:27","extension":"png","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":106355,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/28ce9a4049e718d1db111e78.png"},{"id":98432581,"identity":"591cc418-3f68-4ce9-9097-abdfa2d9dace","added_by":"auto","created_at":"2025-12-17 16:49:43","extension":"png","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":149750,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/add6588e9a3ed01e612a5d39.png"},{"id":98432777,"identity":"e949eef8-8722-4580-8d61-4031fcc0c117","added_by":"auto","created_at":"2025-12-17 16:49:57","extension":"png","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":119174,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/8f850009db4af47e48f511b2.png"},{"id":98434147,"identity":"98d77454-e56c-4f2a-89d7-d3b895c49810","added_by":"auto","created_at":"2025-12-17 16:51:35","extension":"png","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":227222,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/b9a9ebbe1f3334a9e5365934.png"},{"id":98433820,"identity":"781c5a36-9483-49bb-bacf-f2fcfb8f2fda","added_by":"auto","created_at":"2025-12-17 16:51:09","extension":"png","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":122270,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/451e5405d20270b151561b70.png"},{"id":98225968,"identity":"47ec15e4-24c4-494a-9d99-6762798974e9","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"png","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":652748,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/19e95dda141bcb2505fc2fb2.png"},{"id":98432780,"identity":"4321c657-857f-4e0b-a1e9-43ae00de45ab","added_by":"auto","created_at":"2025-12-17 16:49:58","extension":"png","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":216310,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/a404bc8ee1524cf885a9419b.png"},{"id":98434062,"identity":"6f3c24f1-5d37-464d-a0ef-2de049ef9b74","added_by":"auto","created_at":"2025-12-17 16:51:28","extension":"png","order_by":42,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1489,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/39b799f71928215740926882.png"},{"id":98225976,"identity":"5f389a53-73d6-4372-8fde-9ddeeb7314ce","added_by":"auto","created_at":"2025-12-15 12:36:55","extension":"png","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1095,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/f8ca1403969fac6ba59e870c.png"},{"id":98225971,"identity":"383723bc-a948-4010-a37e-50083374d9d3","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"png","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1089,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/c3e474586a3211b38a7f2ccd.png"},{"id":98434064,"identity":"0005dc15-9266-4f6e-b6e1-9f60f16b4ee3","added_by":"auto","created_at":"2025-12-17 16:51:28","extension":"png","order_by":45,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1678,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/126a2641303d3ee97c807330.png"},{"id":98225966,"identity":"1c6f51fc-24e2-40f0-b2ed-90e08ded27d8","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"png","order_by":46,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1307,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/d08f1b95032b3c0d96b753f8.png"},{"id":98225964,"identity":"625890e8-6644-4e36-bc8e-f7e818ccfad2","added_by":"auto","created_at":"2025-12-15 12:36:54","extension":"xml","order_by":47,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":170980,"visible":true,"origin":"","legend":"","description":"","filename":"fd6763aa9b734200971df1d84a50a1171structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/d8457c1e58e3d89efce5c220.xml"},{"id":98431880,"identity":"b0876a1e-6af7-439d-bde4-537dd043896e","added_by":"auto","created_at":"2025-12-17 16:48:32","extension":"html","order_by":48,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":190638,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1/7343b152af8a95e1c4af62e5.html"},{"id":98622146,"identity":"cd99b5c8-6244-44b5-a00f-c9a4910f519e","added_by":"auto","created_at":"2025-12-19 16:46:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2846172,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8272325/v1_covered_9788e4ed-9a4c-4e33-a113-66a2020dd3b4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Intrusion Detection Based on Federated Context-Aware Embedded Deep Transfer Learning in Heterogeneous Networks","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"knowledge-and-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"kais","sideBox":"Learn more about [Knowledge and Information Systems](http://link.springer.com/journal/10115)","snPcode":"10115","submissionUrl":"https://submission.nature.com/new-submission/10115/3","title":"Knowledge and Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Heterogeneous Fusion, Deep Learning, Word Embedding, Federated Learning, Intrusion Detection","lastPublishedDoi":"10.21203/rs.3.rs-8272325/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8272325/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWith the continuous advancement of the Internet of Everything paradigm, network intrusion detection systems (IDS) are confronted with multiple challenges in heterogeneous data sharing, integration, and security. To address these issues, this paper proposes a theoretical framework based on Word Embedded Federated Deep Transfer Learning (WE-FDTL) under the dual constraints of inconsistent data distribution and privacy preservation in heterogeneous network environments. The core innovation lies in establishing a latent vector-driven federated semantic aggregation mechanism to achieve cross-domain distributed representation alignment and knowledge fusion. At the representation learning level, a semantic space mapping model is constructed using contextual word embedding techniques to transform discrete heterogeneous network sequences into continuous dense vectors. This approach eliminates the need for explicit data standardization while preserving structural information in high-dimensional space and ensuring embedded privacy protection. For feature alignment, we propose a domain adaptation method based on latent space projection. By establishing latent space alignment constraints across participants, this method achieves cross-domain feature alignment and unified representation, while enabling effective adaptation of latent space matrices to mainstream deep learning models, thereby addressing the domain shift problem in heterogeneous federated transfer learning. At the federated optimization level, a semantically embedded federated aggregation mechanism is designed to facilitate global cross-domain knowledge sharing and integration through gradient transmission in latent vector space instead of raw data exchange. This framework ensures data privacy at terminal devices while maintaining effective knowledge fusion. In simulation experiments, six deep learning models were employed to evaluate multi-class classification performance across three scenarios: single-source domain deep learning, single-source domain federated deep learning, and cross-source domain WE-FDTL. Experimental results on the mixed NSL-KDD and UNSW-NB15 datasets demonstrate that WE-FDTL achieves a client-side training accuracy of 94.88% and a validation accuracy of 90.36%, confirming the theoretical effectiveness and practical advantages of the proposed IDS approach in heterogeneous network environments.\u003c/p\u003e","manuscriptTitle":"Intrusion Detection Based on Federated Context-Aware Embedded Deep Transfer Learning in Heterogeneous Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-15 12:36:48","doi":"10.21203/rs.3.rs-8272325/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"70723680050670048411423454759360929150","date":"2026-05-20T09:14:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-09T21:06:11+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-06T11:33:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-06T04:48:38+00:00","index":"","fulltext":""},{"type":"submitted","content":"Knowledge and Information Systems","date":"2025-12-03T16:11:04+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"knowledge-and-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"kais","sideBox":"Learn more about [Knowledge and Information Systems](http://link.springer.com/journal/10115)","snPcode":"10115","submissionUrl":"https://submission.nature.com/new-submission/10115/3","title":"Knowledge and Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"cdffdbc5-0578-4961-9c6f-6d17259d7beb","owner":[],"postedDate":"December 15th, 2025","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"70723680050670048411423454759360929150","date":"2026-05-20T09:14:36+00:00","index":44,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-12-15T12:36:49+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-15 12:36:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8272325","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8272325","identity":"rs-8272325","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00