[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-462837-105":59,"doc-detail-462837-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","a-framework-for-budget-constrained-zero-day-cyber-threat-mitigation-a-knowledge-guided-reinforcement-learning-approach","A Framework for Budget-Constrained Zero-Day Cyber Threat Mitigation - A Knowledge-Guided Reinforcement Learning Approach","","Conventional machine-learning defenses fail to generalize to unseen ATT&CK action chains, especially under limited telemetry budgets where causal explainability and auditing are hard to provide. A knowledge-based framework is proposed that combines grammar-constrained ATT&CK model generation, budget-constrained reinforcement learning, and graph-based causal explanation in an auditable pipeline. Zero-day attack chains are synthesized into Zeek-aligned witness telemetry, while a dynamically updated Cyber-Threat Knowledge Graph supports causal decision states and provenance-linked, traceable alerts. Extensive evaluations on zero-day TTP holdouts show improved low-FPR accuracy, TTD, and calibration.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-framework-for-budget-constrained-zero-day-cyber-threat-mitigation-a-knowledge-guided-reinforcement-learning-approach/462837/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/a-framework-for-budget-constrained-zero-day-cyber-threat-mitigation-a-knowledge-guided-reinforcement-learning-approach/462837.png","ImageObject",300,407,{"name":92,"@type":93},"Jasmine","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-09","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":56},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What limitations of conventional machine-learning defenses motivate this framework?","Question",{"text":112,"@type":113},"Conventional defenses struggle to generalize to novel ATT&CK action chains and are inefficient under low telemetry budgets. They also provide brittle or incomplete causal explainability and auditing for generated alerts.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the framework generate and compile zero-day attack chains for training?",{"text":117,"@type":113},"It uses a grammar-constrained generator tied to an ATT&CK database to synthesize unseen zero-day technique chains, then compiles each chain into Zeek-aligned witness telemetry for network and host logs.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the Cyber-Threat Knowledge Graph (CTKG) contribute to decision-making and explanations?",{"text":121,"@type":113},"CTKG stores dynamically updated semantics linking tactics, techniques, hosts, and vulnerabilities, enabling causal relations to enhance the decision state. It supports causal CTKG slices for counterfactual probes and helps provide traceable, provenance-linked explanations for alerts.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},462837,1791156548,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":56,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":36,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":19,"preview_urls":145},2336478487870,"https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","Article  \nA Framework for Budget-Constrained Zero-Day Cyber Threat Mitigation: A Knowledge-Guided Reinforcement  \nLearning Approach  \nMainak Basak and Geon-Yun Shin *  \nAcademic Editor: Maurizio Talamo  \nReceived: 19 November 2025  \nRevised: 12 December 2025  \nAccepted: 17 December 2025  \nPublished: 19 December 2025  \nCopyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.  \nSchool of Computer Engineering & Applied Mathematics, Hankyong National University, Anseong-si 17579, Republic of Korea  \n* Correspondence: [gunyoon.shin@hknu.ac.kr](gunyoon.shin@hknu.ac.kr)  \nAbstract  \nConventional machine-learning-based defenses are unable to generalize well to novel chains of ATT&CK actions. Being inefficient with low telemetry budgets, they are also unable to provide causal explainability and auditing. We propose a knowledge-based cyber-defense framework that integrates ATT&CK constrained model generation, budgetconstrained reinforcement learning, and graph-based causal explanation into a single auditable pipeline. The framework formalizes the synthesis of zero-day chains of attacks using a grammar-formalized ATT&CK database and compiles them into the Zeek-aligned witness telemetry. This allows for efficient training of detection using the generated data within limited sensor budgets. The Cyber-Threat Knowledge Graph (CTKG) stores dynamically updated inter-relational semantics between tactics, techniques, hosts, and vulnerabilities. This enhances the decision state using causal relations. The sensor budget policy selects the sensoring and containment decisions within explicit bounds of costs and latency. The inherent defense-provenance features enable a traceable explanation of each generated alarm. Extensive evaluations of the framework using the TTP holdouts of the zero-day instances show remarkable improvements over conventional techniques in terms of low-FPR accuracy, TTD, and calibration.  \nKeywords: Cyber-Threat Knowledge Graph; MITRE ATT&CK; generative cyber range; reinforcement learning for cyber defense; zero-day TTP  \n1. Introduction  \nModern enterprise’s cyber-defense frameworks encounter three persistent deficiencies. First, it is challenging for detection models to address unseen attack chains that follow the ATT&CK ontology but differ in order, preconditions and tooling [1] . Second, telemetry isnot free of charge. The teams operate under tight budgets for log volume, CPU, storage, and latency [2,3] . Third, the explanations are brittle under shifts and are generally not tied to the causal structures of tactics and techniques. Many systems cannot demonstrate which model, which knowledge state, or which configuration produced a given alert [4] . Public datasets and cyber simulation labs help. However, they leave these gaps open. The packet and flow corpora are static in nature. Red team replays are scripted. Most gym environments simulate fixed attack playbooks [2,5] . Logging is usually all-on or fixed per scenario. Causal semantics over ATT&CK are not exposed to the defender or to the evaluation harness. Artifacts such as alerts and explanations are saved as files without verifiable  \nprovenance. As a result, we cannot study cost-aware defense, generalization to zero-day chains, or explanation stability in a controlled and reproducible way [6–8] .  \nWe address these needs with Sim-CTKG, an ATT&CK-aware generative cyber range for reinforcement learning and defense [9] . Nodes represent tactics, techniques, software, hosts, and CVEs [10,11] . Edges encode preconditions and effects that link actions and entities. Sim-CTKG samples unseen technique chains with a formal grammar that respects ATT&CK constraints, then compiles each chain into witness telemetry for network and host logs. The defender observes features and a two-hop CTKG slice each step and learns a sensor-budget poli","cbCaiqxvi30KICq7","https://ap.wps.com/l/cbCaiqxvi30KICq7","pdf",6062320,"English","# Introduction\n## Sim-CTKG for Budget-Constrained Zero-Day Defense\n## Key Contributions","[{\"question\":\"What limitations of conventional machine-learning defenses motivate this framework?\",\"answer\":\"Conventional defenses struggle to generalize to novel ATT\\u0026CK action chains and are inefficient under low telemetry budgets. They also provide brittle or incomplete causal explainability and auditing for generated alerts.\"},{\"question\":\"How does the framework generate and compile zero-day attack chains for training?\",\"answer\":\"It uses a grammar-constrained generator tied to an ATT\\u0026CK database to synthesize unseen zero-day technique chains, then compiles each chain into Zeek-aligned witness telemetry for network and host logs.\"},{\"question\":\"How does the Cyber-Threat Knowledge Graph (CTKG) contribute to decision-making and explanations?\",\"answer\":\"CTKG stores dynamically updated semantics linking tactics, techniques, hosts, and vulnerabilities, enabling causal relations to enhance the decision state. It supports causal CTKG slices for counterfactual probes and helps provide traceable, provenance-linked explanations for alerts.\"}]","A Framework for Budget-Constrained Zero-Day Cyber Threat Mitigation - A Knowledge-Guided Reinforcement Learning Approach | PDF",1790765416,101,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/53d3585d291d2957d4afc05417cf0bea.webp",983,1390,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/135600b6866cadb23e8bc1b09a54933f.webp",982,1388,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/d06ae357711c7cf51198da380c50f1b5.webp",981,1387,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/8ccec1356f3adacc67e586e78971c0e7.webp",980,1385]