[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-31679":3,"doc-seo-31679":27},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"file_id":15,"file_url":16,"file_type":17,"file_size":18,"view_count":4,"is_deleted":4,"is_public":19,"is_downloadable":19,"audit_status":19,"page_count":20,"language":21,"language_code":22,"table_of_contents":23,"faqs":24,"seo_title":13,"seo_description":14,"update_tm":25,"read_time":26},31679,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Stacked HRDGL A Fast Hybrid Model for Real-Time Network Intrusion Detection","Growing network attacks, including DDoS and darknet traffic anomalies, demand network intrusion detection systems (NIDS) that are both accurate and truly real-time. XGBoost delivers strong accuracy but may not meet strict latency requirements, motivating an efficient alternative. The paper presents Stacked HRDGL, a dynamic hybrid stacked ensemble that reduces inter-model redundancy using Logistic Regression, Naive Bayes, Decision Tree, and Random Forest with a fast meta-learning scheme. On CICIDS2017 and CICDarknet2020, it reaches 99.98% and 94.03% accuracy while cutting latency up to 15x versus XGBoost, supporting scalable deployment.","cbCaimsThM1hTVvH","https://ap.wps.com/l/cbCaimsThM1hTVvH","pdf",1874525,1,5,"English","en","# Introduction\n# Related Work","[{\"question\":\"What problem does Stacked HRDGL address in real-time NIDS?\",\"answer\":\"Stacked HRDGL targets the accuracy–latency trade-off, where high-performing models like XGBoost can miss real-time low-latency requirements. It aims to optimize both detection speed and classification accuracy.\"},{\"question\":\"How does Stacked HRDGL combine multiple models?\",\"answer\":\"The approach uses a stacked hybrid ensemble with Logistic Regression, Naive Bayes, Decision Tree, and Random Forest as base learners. Logistic Regression is used as the meta-learner to integrate base outputs for faster, more robust decisions.\"},{\"question\":\"How effective is Stacked HRDGL on the reported datasets?\",\"answer\":\"The paper reports competitive results on CICIDS2017 and CICDarknet2020, achieving 99.98% and 94.03% accuracy. It also reduces latency by up to 15x compared with XGBoost, measured on a standard multicore system.\"}]",1779915637,13,{"code":4,"msg":28,"data":29},"ok",{"site_id":30,"language":22,"slug":31,"title":13,"keywords":32,"description":14,"schema_data":33,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":25},105,"stacked-hrdgl-a-fast-hybrid-model-for-real-time-network-intrusion-detection","",{"@graph":34,"@context":83},[35,52,66],{"@type":36,"itemListElement":37},"BreadcrumbList",[38,42,46,49],{"item":39,"name":40,"@type":41,"position":19},"https://docshare.wps.com","Home","ListItem",{"item":43,"name":44,"@type":41,"position":45},"https://docshare.wps.com/document/","Document",2,{"item":47,"name":12,"@type":41,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":41,"position":51},"https://docshare.wps.com/document/stacked-hrdgl-a-fast-hybrid-model-for-real-time-network-intrusion-detection/31679/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-05-27",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What problem does Stacked HRDGL address in real-time NIDS?","Question",{"text":73,"@type":74},"Stacked HRDGL targets the accuracy–latency trade-off, where high-performing models like XGBoost can miss real-time low-latency requirements. It aims to optimize both detection speed and classification accuracy.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"How does Stacked HRDGL combine multiple models?",{"text":78,"@type":74},"The approach uses a stacked hybrid ensemble with Logistic Regression, Naive Bayes, Decision Tree, and Random Forest as base learners. Logistic Regression is used as the meta-learner to integrate base outputs for faster, more robust decisions.",{"name":80,"@type":71,"acceptedAnswer":81},"How effective is Stacked HRDGL on the reported datasets?",{"text":82,"@type":74},"The paper reports competitive results on CICIDS2017 and CICDarknet2020, achieving 99.98% and 94.03% accuracy. It also reduces latency by up to 15x compared with XGBoost, measured on a standard multicore system.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":30}]