[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82580-en":3,"doc-seo-82580-105":29,"detail-sidebar-cat-0-en-105":91},{"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,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82580,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Data-driven mitigation of catastrophic forgetting in dynamic physical layer attack detection","Optical networks rely on timely, accurate detection of physical-layer intrusions to prevent service disruptions and eavesdropping. Dynamic intrusion detection models adapt using newly acquired telemetry, but they can suffer catastrophic forgetting when previously seen attacks reappear after long absence, creating a tradeoff between adaptability and long-term knowledge retention. The paper proposes a data-driven mechanism that balances update datasets with parts of past attack data, using an accuracy-drop threshold to trigger balancing, reducing adaptation time by 37% versus a non-balancing dynamic baseline.","arXiv :2607 .0 104 1v 1 [ cs .NI] 1 Jul 2026  \n\n| Research Article | 1 |\n| --- | --- |\n\nData-driven mitigation of catastrophic forgetting in dynamic physical layer attack detection  \nALEKSANDRA KNAPI´NSKA 1,* AND MARIJA FURDEK2  \n1 Department of Systems and Computer Networks, Wrocław University of Science and Technology, Wrocław, Poland  \n2 Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden  \n* [aleksandra.knapinska@pwr.edu.pl](aleksandra.knapinska@pwr.edu.pl)  \nCompiled July 2, 2026  \nOptical networks are critical infrastructure that underpins global communications, and detecting security breaches that jeopardize them is essential to maintaining worldwide connectivity. As malicious actors continuously evolve their attack techniques, dynamically updated intrusion detection models have become a key component of modern defense mechanisms. By incorporating newly acquired telemetry data, these models can adapt to emerging threats while maintaining high detection performance. However, when previously encountered attacks reappear after a prolonged period of absence, adaptive models may fail to recognize them due to the phenomenon of catastrophic forgetting. In contrast, statically trained models can reliably detect attacks represented in the original training data but lack the ability to adapt to previously unseen attack patterns. Consequently, intrusion detection systems face a fundamental tradeoff between adaptability to evolving threats and long-term retention of previously acquired knowledge. In this work, we propose a data-driven mechanism to cope with catastrophic forgetting in dynamic attack detection systems. Our approach balances the model update datasets by using parts of past attack data. We utilize a threshold-based mechanism to trigger data balancing after accuracy drops due to an active attack change. Applied to an experimental optical network security dataset, the proposed approach reduces the average model adaptation time by 37% compared to its dynamic counterpart that does not employ data balancing. Compared to a baseline from the literature that relies on neural network depth increasing, our approach requires 6% fewer data batches to adapt to changing conditions and regain performance.  \n[http://dx.doi.org/10.1364/ao.XX.XXXXXX](http://dx.doi.org/10.1364/ao.XX.XXXXXX)  \n1. INTRODUCTION  \nOptical networks constitute the fundamental infrastructure supporting global communications. As a critical component, they are increasingly targeted by harmful activities and intrusions that may result with service disruptions or eavesdropping. Service degradation at the optical layer can be caused by, for example, targeted fiber cuts, insertion of harmful jamming signals, or polarization scrambling. Eavesdropping can be performed, for example, by fiber tapping via fiber bending or monitoring port access [1, 2] . Due to the extremely high data rates employed in optical networks, even short interruptions at the optical layer may result with large amount of data being lost, compromisedor corrupt. Physical-layer breaches may also propagate to upperlayer services, potentially causing cascading and wide-spread service failures [3] .  \nMaintaining service continuity in the presence of physicallayer breaches requires their timely and accurate detection, and tailored response. Real-time monitoring of the physical layer is paramount to its secure operation [4] . In this context, secu-  \nrity monitoring methods based on Machine Learning (ML) are continuously developed to protect the network in an automated manner [5] . Various ML techniques have been demonstrated as paramount for optical network security management. They excel in identifying the related intricate and subtle effects in order to distinguish the causes of the known types of threats [6, 7] as well as detect various novel physical-layer breaches [8] . In multiclass scenarios, concrete attack types can be recognized based on the samples pres","cbCaiuFbX4Lcl6a9","https://ap.wps.com/l/cbCaiuFbX4Lcl6a9","pdf",1049328,1,10,"English","en",105,"# Introduction\n## Optical networks as critical infrastructure\n## Threats and need for real-time detection\n## Machine learning for physical-layer monitoring\n## Dynamic models, concept drift, and catastrophic forgetting","[{\"question\":\"What problem does the paper address in dynamic physical-layer attack detection?\",\"answer\":\"Dynamic models that adapt to new telemetry can fail when older attacks return after a long period, due to catastrophic forgetting.\"},{\"question\":\"How does the proposed method mitigate catastrophic forgetting?\",\"answer\":\"It balances model update datasets using portions of past attack data, triggered by a threshold mechanism after accuracy drops caused by attack changes.\"},{\"question\":\"What performance improvements are reported?\",\"answer\":\"On an experimental optical network security dataset, the approach reduces average model adaptation time by 37% versus a dynamic counterpart without data balancing, and it needs 6% fewer data batches than a literature baseline that increases neural network depth.\"}]",1784181620,25,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"data-driven-mitigation-of-catastrophic-forgetting-in-dynamic-physical-layer-attack-detection","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/data-driven-mitigation-of-catastrophic-forgetting-in-dynamic-physical-layer-attack-detection/82580/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in dynamic physical-layer attack detection?","Question",{"text":75,"@type":76},"Dynamic models that adapt to new telemetry can fail when older attacks return after a long period, due to catastrophic forgetting.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method mitigate catastrophic forgetting?",{"text":80,"@type":76},"It balances model update datasets using portions of past attack data, triggered by a threshold mechanism after accuracy drops caused by attack changes.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance improvements are reported?",{"text":84,"@type":76},"On an experimental optical network security dataset, the approach reduces average model adaptation time by 37% versus a dynamic counterpart without data balancing, and it needs 6% fewer data batches than a literature baseline that increases neural network depth.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]