基于 LLM 辅助判断的在线对话欺诈与概念漂移联合检测方法
Joint Detection of Fraud and Concept Drift inOnline Conversations with LLM-Assisted Judgment
AI 导读
arXiv 论文提出两阶段检测框架，先用集成分类模型识别可疑对话，再用 One Class Drift Detector（OCDD）分析其中的概念漂移；检测到漂移时由大语言模型（LLM）判断漂移源于欺诈操纵还是正常话题切换，未检测到漂移则归为类垃圾行为。作者在社交工程聊天场景数据集上验证，该模块化方法在实时欺诈检测的准确率和可解释性上均有提升，并与 Dual LLM 基线做了对比。
正文 · 原文
Abstract:Detecting fake interactions in digital communication platforms remains a challenging and insufficiently addressed problem. These interactions may appear as harmless spam or escalate into sophisticated scam attempts, making it difficult to flag malicious intent early. Traditional detection methods often rely on static anomaly detection techniques that fail to adapt to dynamic conversational shifts. One key limitation is the misinterpretation of benign topic transitions referred to as concept drift as fraudulent behavior, leading to either false alarms or missed threats. We propose a two stage detection framework that first identifies suspicious conversations using a tailored ensemble classification model. To improve the reliability of detection, we incorporate a concept drift analysis step using a One Class Drift Detector (OCDD) to isolate conversational shifts within flagged dialogues. When drift is detected, a large language model (LLM) assesses whether the shift indicates fraudulent manipulation or a legitimate topic change. In cases where no drift is found, the behavior is inferred to be spam like. We validate our framework using a dataset of social engineering chat scenarios and demonstrate its practical advantages in improving both accuracy and interpretability for real time fraud detection. To contextualize the trade offs, we compare our modular approach against a Dual LLM baseline that performs detection and judgment using different language models.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2505.07852 [cs.CL] |
| (or arXiv:2505.07852v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2505.07852 arXiv-issued DOI via DataCite |
Submission history
From: Ali Şenol [view email]
[v1]
Wed, 7 May 2025 22:30:53 UTC (577 KB)
[v2]
Thu, 29 Oct 2026 11:39:23 UTC (636 KB)
来源：arXiv cs.AI · arxiv.org