[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82277-en":3,"doc-seo-82277-105":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},82277,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Blockchain Linked Auditable Decision Management for Telecom IoT Fraud Control Requests","Telecom fraud-control research often ends at detector-level classification, yet real deployment needs request-level policy resolution, lifecycle traceability, and auditability. The paper reframes fraud control as blockchain-linked auditable decision management for synthetic telecom/IoT fraud-control requests. A QLoRA-tuned LLM branch becomes substantially more usable than zero-shot prompting, but mostly approaches rather than surpasses a lower-cost centralized ensemble. The framework models each synthetic deployment record as a managed request, enforces out-of-boundary handling via a deterministic hard-fraud gate, scores remaining requests with centralized, federated, or LLM-family risk sources, and resolves actions through a shared five-state policy plus an Ethereum-compatible audit layer. Controlled drift-replay evaluation emphasizes replay evidence over field validation.","Blockchain-Linked Auditable Decision Management for Telecom/IoT Fraud-Control Requests  \nSaviz Changizi, Nasibeh Mohammadzadeh, Mohammad Shojafar, and Rahim Tafazolli  \narXiv :2607 .09259v 1 [ cs .CR] 10 Jul 2026  \nAbstract—Telecom fraud-control studies often stop at detectorlevel classification, but deployment use requires request-level policy resolution, lifecycle traceability, and auditability. This paper reframes fraud control as blockchain-linked auditable decision management for synthetic telecom/IoT fraud-control requests, and its main result is that the QLoRA-tuned LLM branch becomes much more usable than zero-shot prompting but mainly approaches, rather than outperforms, a lower-cost centralized ensemble. The framework maps each synthetic deployment record to a managed request, blocks explicit outof-boundary cases through a deterministic hard-fraud gate, scores non-hard requests using centralized ML (M1), federated meta-learning (M2), or LLM-family risk sources (M3), andresolves actions through a shared five-state policy, two-zone refinement mechanism, and local Ethereum-compatible audit layer. Evaluation uses separate synthetic training data and a 100,000-record deployment replay corpus, so the study should be read as controlled drift-replay evidence rather than field validation or proof of live deployability. On validation, M1 gives the strongest balance, with legitimate-request FPR 0.0890 under the 0.10 operating cap and soft-fraud recall 0.8341. On labeled deployment replay, however, the legitimate-FPR gap becomes large: M1 rises to 0.1646 and M3-QLoRA to 0.1801, while M3-QLoRA reduces the M3-Base legitimate FPR from 0.3915 and reaches 0.8240 soft-fraud recall. Blockchain telemetry shows that lifecycle gas, cost, latency, and throughput differences are driven by submitted off-chain decision profiles rather than changes in fraud logic.  \nIndex Terms—Telecom fraud control, IoT security, auditable decision management, blockchain audit, federated learning, large language models, QLoRA, deployment replay.  \nI. INTRODUCTION  \nTelecom fraud detection has been framed as a critical problem in telecom networks because fraudulent activity can threaten users’ privacy and property security [1] . Industry reports further indicate the economic scale of the problem, with the Communications Fraud Control Association (CFCA) estimating global telecommunications fraud losses at USD 38.95 billion in 2023, equivalent to 2.5% of telecommunications revenues [2] . More recent industry reporting citing the latest CFCA Fraud Loss Survey indicates that global telecom fraud losses increased further to approximately USD 41.82 billion by 2025 [3] . Wangiri fraud provides a concrete telecom-fraud example: it exploits missed calls and premiumrate numbers and has commonly been studied using Call Detail Record (CDR)-style telecom data [4] .  \nSaviz Changizi, Mohammad Shojafar, and Rahim Tafazolli are with the 6G Innovation Centre, Institute for Communication Systems, University of Surrey, UK (e-mail: {s.changizi, m.shojafar, [r.tafazolli}@surrey.ac.uk](r.tafazolli}@surrey.ac.uk)).  \nNasibeh Mohammadzadeh is with the Department of Network Engineering, Polytechnic University of Catalonia, Barcelona, Spain (e-mail: nasi[beh.m@gmail.com](beh.m@gmail.com)).  \nAt the network-management level, sixth-generation (6G) -oriented telecom environments are shaped by requirements such as ultra-low latency, ultra-dense connections, high reliability, low power consumption, energy efficiency, intelligence, and security [5] . In 6G-Internet of Things (IoT) resourcemanagement settings, relevant quality-of-service and resourcemanagement variables include delay, bandwidth utilization, power consumption, throughput, device mobility, and location [6] .  \nStatic thresholds and predefined rules may fail to adapt to evolving fraud patterns, leading to false positives or missed fraud cases, and highly imbalanced, unlabeled CDR data further complicate fraud-model training and ","cbCaiiOdZdowows8","https://ap.wps.com/l/cbCaiiOdZdowows8","pdf",1671703,2,1,16,"English","en",105,"# Introduction\n## Motivation and problem context\n## Deployment needs beyond detector-level classification\n# Framework overview\n## Managed requests and deterministic hard-fraud gating\n## Risk scoring with centralized, federated meta-learning, and LLM sources\n## Five-state policy and Ethereum-compatible audit layer\n# Evaluation setup and results\n## Validation metrics and operating constraints\n## Deployment replay analysis and drift behavior\n## Blockchain telemetry interpretation","[{\"question\":\"What deployment capabilities does the paper argue are missing from detector-level telecom fraud studies?\",\"answer\":\"The paper emphasizes request-level policy resolution, execution control, lifecycle traceability, and auditable decision handling, which go beyond detecting suspicious records.\"},{\"question\":\"How does the proposed framework handle out-of-boundary fraud cases?\",\"answer\":\"It blocks explicit out-of-boundary cases using a deterministic hard-fraud gate, while non-hard requests are processed by separate risk-scoring modules.\"},{\"question\":\"Which scoring approach performs best under the paper’s validation setting and what trade-off appears in deployment replay?\",\"answer\":\"On validation, M1 provides the strongest balance with legitimate-request FPR 0.0890 under a 0.10 cap and soft-fraud recall 0.8341. In labeled deployment replay, the legitimate-FPR gap grows: M1 increases to 0.1646 and M3-QLoRA to 0.1801, while M3-QLoRA improves soft-fraud recall to 0.8240.\"}]",1784179338,40,{"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},"blockchain-linked-auditable-decision-management-for-telecom-iot-fraud-control-requests","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/blockchain-linked-auditable-decision-management-for-telecom-iot-fraud-control-requests/82277/",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","2026-07-22","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 deployment capabilities does the paper argue are missing from detector-level telecom fraud studies?","Question",{"text":75,"@type":76},"The paper emphasizes request-level policy resolution, execution control, lifecycle traceability, and auditable decision handling, which go beyond detecting suspicious records.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed framework handle out-of-boundary fraud cases?",{"text":80,"@type":76},"It blocks explicit out-of-boundary cases using a deterministic hard-fraud gate, while non-hard requests are processed by separate risk-scoring modules.",{"name":82,"@type":73,"acceptedAnswer":83},"Which scoring approach performs best under the paper’s validation setting and what trade-off appears in deployment replay?",{"text":84,"@type":76},"On validation, M1 provides the strongest balance with legitimate-request FPR 0.0890 under a 0.10 cap and soft-fraud recall 0.8341. In labeled deployment replay, the legitimate-FPR gap grows: M1 increases to 0.1646 and M3-QLoRA to 0.1801, while M3-QLoRA improves soft-fraud recall to 0.8240.","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},[93,97,101,105,110,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"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":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]