Blockchain-Linked Auditable Decision Management for Telecom/IoT Fraud-Control Requests

2026-07-10

AI Summary

This work addresses the lack of request-level decision-making, end-to-end traceability, and auditability in telecommunications and IoT fraud prevention by proposing an auditable decision system that integrates a blockchain-based audit layer with multi-source risk scoring. The system first applies a deterministic hard-fraud gating mechanism to filter clearly anomalous requests; for the remaining requests, it computes risk scores using either centralized machine learning, federated meta-learning, or QLoRA-finetuned large language models. Response actions are then generated via a five-state policy engine and a dual-zone refinement mechanism, with all decisions immutably recorded on a local Ethereum-compatible audit chain. Experiments demonstrate that the M3-QLoRA model reduces the base LLM’s false positive rate from 0.3915 to 0.1801 while achieving a recall of 0.8240, thereby establishing the first request-level traceable and auditable fraud prevention framework.

Abstract

Telecom fraud-control studies often stop at detector-level 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 out-of-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), and resolves 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.

Problem

• telecom fraud control
• request-level policy
• lifecycle traceability
• auditability
• blockchain-linked decision management

Innovation

• blockchain-auditable decision management
• QLoRA-tuned LLM
• federated meta-learning
• hard-fraud gate
• Ethereum-compatible audit layer