arXiv：cs.AI· Saviz Changizi, Nasibeh Mohammadzadeh, Mohammad Shojafar, Rahim Tafazolli·· 6 小时前AI 评分33
AI 监督何时有效？基于区块链可审计的网络欺诈决策管理角色感知研究
When Does AI Supervision Help? A Role-Aware Study of Network Fraud Decision Management with Blockchain Auditability
AI 导读
研究通过角色感知的 Decider-Supervisor（DS）框架评估 AI 监督对网络欺诈决策的价值，对比集中式机器学习、FedAvg 联邦元模型和 Base/QLoRA 大语言模型四种配置。
正文
Abstract:When does a second artificial intelligence (AI) component improve a primary network-fraud decision rather than add operational burden? We study this question through a role-aware Decider-Supervisor (DS) framework with blockchain auditability, evaluating four directional configurations that combine centralised machine learning, a Federated Averaging (FedAvg)-trained federated meta-model, and Base or Quantized Low-Rank Adaptation (QLoRA) large language model variants. The analysis compares primary-only and supervised decisions using non-hard fraud performance, intervention burden, conditional calibration, traffic-mix and Review-capacity sensitivity, dependability tests, and blockchain lifecycle controls. The deterministic hard gate resolves 89.994% of fraudulent requests, leaving the non-hard population as the main AI decision setting. Conditional validation calibration does not produce a consistently transferable supervisory advantage on deployment replay. DS-3 QLoRA is the least disruptive supervised configuration, but it still underperforms its primary FedAvg stage in F1 and total errors. Across 36 reweighted traffic mixtures, supervision reduces total errors only for DS-4 Base in two extreme high-fraud scenarios. Blockchain tests support digest verification, tamper detection, authorisation, single-use review resolution, and post-finalisation integrity, while exposing a pre-finalisation single-write limitation. The results show that the value of AI supervision depends on role assignment, calibration, escalation policy, traffic composition, and lifecycle controls rather than on the presence of a second model alone.
| Comments: | 27 pages, 10 figures, 13 tables |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.07434 [cs.AI] |
| (or arXiv:2610.07434v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07434 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Saviz Changizi [view email]
[v1]
Mon, 5 Oct 2026 21:40:07 UTC (214 KB)
来源：arXiv：cs.AI · arxiv.org