[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82760-en":3,"doc-seo-82760-105":30,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},82760,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Swarm-Driven Multi-Agent Reasoning for Smart City Security","Modern smart cities operate as complex, interconnected cyber-physical ecosystems where thousands of heterogeneous devices exchange data and control commands. Threats can evade local detection through low-rate sensing scans, irregular credential usage, protocol misuse, and delayed cross-gateway movement, collectively signaling coordinated multi-stage campaigns. TPSCSec introduces an LLM-based multi-agent framework for stable, reliable security reasoning under uncertainty, partial observability, and adversarial manipulation. A threat-pheromone swarm consensus aggregates independent agents’ hypotheses. Adaptive Verified TPSC further calibrates verification and disagreement handling to improve consistency and acceptance.","Swarm-Driven Multi-Agent Reasoning for Smart  \nCity Security  \nSaeid Jamshidi, Carol Fung, Kawser Wazed Nafi, Foutse Khomh  \narXiv :2607 .03628v 1 [ cs .CR] 3 Jul 2026  \nAbstract—Modern smart cities operate as complex, interconnected cyber-physical ecosystems in which thousands of heterogeneous devices continuously exchange data and control commands. In these environments, advanced threats often differ from conventional isolated incidents; i.e., a low-rate scan of traffic sensors, irregular credential usage across edge devices, protocol misuse, and delayed lateral movement across gateways may each remain below local alert thresholds but collectively indicate a coordinated multi-stage campaign. Therefore, security in smart cities remains not only an attack detection problem but also a reasoning problem under uncertainty, partial observability, and adversarial manipulation. In this work, we present TPSCSec, an LLM-based multi-agent approach for stable and reliable security reasoning in smart cities. In contrast to a single-agent model, which may overlook distributed indicators and produce unstable interpretations, TPSC-Sec decomposes security analysis across specialized agents that examine traffic behavior, protocol interactions, identity usage, and temporal attack progression. These agents generate independent threat hypotheses from partial observations, which are then aggregated through the proposed Threat-Pheromone Swarm Consensus (TPSC) mechanism. TPSC tracks hypothesis-support dynamics through reinforcement, contradiction handling, and temporal consistency, enabling competing threat interpretations to converge toward a stable collective decision. We further introduce Adaptive Verified TPSC (AV-TPSC), which adds verification-aware calibration, contextsensitive weighting, and disagreement-adaptive control to reduce unsupported LLM outputs and reasoning inconsistencies under adversarial conditions. Experimental results over 500 runs show that TPSC-Sec achieves stable consensus formation with a high acceptance rate of 0.97 ± 0.02, strong hypothesis-support concentration (> 0.99), and a consensus margin of 2.08 ± 0.21. The system maintains low aggregate risk (0 .23±0 .04), high inter-agent agreement (0 .82 ± 0 .06), and strong support-quality correlation (r = 0 .93). Adaptive agent selection further reduces the number of active agents by 50% while improving overall system fitness by 11.6% . These results demonstrate that TPSC-Sec enables robust, interpretable, and computationally efficient security reasoning for adversary-resilient smart-city environments.  \nIndex Terms—Multi-Agent LLMs, Swarm-Based Consensus, Adversarial Robustness, Distributed Reasoning, and Semantic Security Intelligence.  \nI. INTRODUCTION  \nThe rapid evolution of smart city infrastructure has enabled the large-scale deployment of Internet of Things (IoT) systems that integrate sensing, communication, and control across critical services such as transportation, energy, healthcare,  \nK. W. Nafi and F. Khomh is with the SWAT Laboratory, Polytechnique Montral, Montral, QC, Canada (e-mail: {kawser.wazed-nafi, [foutse.khomh](foutse.khomh}@polymtl.ca)[}](foutse.khomh}@polymtl.ca)[@polymtl.ca](foutse.khomh}@polymtl.ca)).  \nS. Jamshidi and C. Fung are with the Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montral, QC, Canada (e-mail: {saeid.jamshidi, carol.fung}@concordia.ca) .  \nand public safety [1]–[3] . These systems form highly interconnected cyber-physical ecosystems composed of heterogeneous devices, edge gateways, cloud services, and software controllers operating over dynamic and resource-constrained networks [4]–[6] . While this integration enables intelligent and autonomous city-scale operations, it also expands the attack surface and introduces security challenges that are difficult to address using isolated detection mechanisms [7],[8] . In smart cities, security incidents often emerge from temporally distributed ","cbCaifoztVl7RaT3","https://ap.wps.com/l/cbCaifoztVl7RaT3","pdf",8952044,3,1,19,"English","en",105,"# Abstract\n# Index Terms\n# Introduction","[{\"question\":\"What problem does TPSCSec address in smart city security?\",\"answer\":\"TPSCSec targets security reasoning under uncertainty and adversarial manipulation, where multi-stage attacks may not trigger local alerts individually but indicate coordinated threats collectively.\"},{\"question\":\"How does TPSCSec differ from a single-agent security model?\",\"answer\":\"TPSCSec decomposes analysis across specialized agents that examine traffic behavior, protocol interactions, identity usage, and temporal progression, then aggregates independent threat hypotheses via the Threat-Pheromone Swarm Consensus mechanism.\"},{\"question\":\"What improvements does Adaptive Verified TPSC (AV-TPSC) bring?\",\"answer\":\"AV-TPSC adds verification-aware calibration, context-sensitive weighting, and disagreement-adaptive control to reduce unsupported LLM outputs and reasoning inconsistencies under adversarial conditions.\"}]",1784182750,48,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"swarm-driven-multi-agent-reasoning-for-smart-city-security","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/swarm-driven-multi-agent-reasoning-for-smart-city-security/82760/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","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 TPSCSec address in smart city security?","Question",{"text":75,"@type":76},"TPSCSec targets security reasoning under uncertainty and adversarial manipulation, where multi-stage attacks may not trigger local alerts individually but indicate coordinated threats collectively.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does TPSCSec differ from a single-agent security model?",{"text":80,"@type":76},"TPSCSec decomposes analysis across specialized agents that examine traffic behavior, protocol interactions, identity usage, and temporal progression, then aggregates independent threat hypotheses via the Threat-Pheromone Swarm Consensus mechanism.",{"name":82,"@type":73,"acceptedAnswer":83},"What improvements does Adaptive Verified TPSC (AV-TPSC) bring?",{"text":84,"@type":76},"AV-TPSC adds verification-aware calibration, context-sensitive weighting, and disagreement-adaptive control to reduce unsupported LLM outputs and reasoning inconsistencies under adversarial conditions.","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":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]