当前位置: X-MOL 学术IEEE Trans. Inform. Forensics Secur. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
DFraud鲁: Multi-Component Fraud Detection Free of Cold-Start
IEEE Transactions on Information Forensics and Security ( IF 6.3 ) Pub Date : 2021-05-19 , DOI: 10.1109/tifs.2021.3081258
Saeedreza Shehnepoor , Roberto Togneri , Wei Liu , Mohammed Bennamoun

Fraud review detection is a hot research topic in recent years. The Cold-start is a particularly new but significant problem referring to the failure of a detection system to recognize the authenticity of a new user. State-of-the-art solutions employ a translational knowledge graph embedding approach (TransE) to model the interaction of the components of a review system. However, these approaches suffer from the limitation of TransE in handling N-1 relations and the narrow scope of a single classification task, i.e., detecting fraudsters only. In this paper, we model a review system as a Heterogeneous Information Network (HIN) which enables a unique representation to every component and performs graph inductive learning on the review data through aggregating features of nearby nodes. HIN with graph induction helps to address the camouflage issue (fraudsters with genuine reviews) which has shown to be more severe when it is coupled with cold-start, i.e., new fraudsters with genuine first reviews. In this research, instead of focusing only on one component, detecting either fraud reviews or fraud users (fraudsters), vector representations are learned for each component, enabling multi-component classification. In other words, we can detect fraud reviews, fraudsters, and fraud-targeted items, thus the name of our approach DFraud3. DFraud3 demonstrates a significant accuracy increase of 13% over the state of the art on Yelp.

中文翻译:


DFraud鲁:无需冷启动的多组件欺诈检测



欺诈评论检测是近年来的研究热点。冷启动是一个特别新但重要的问题,指的是检测系统无法识别新用户的真实性。最先进的解决方案采用翻译知识图嵌入方法 (TransE) 来对评论系统组件的交互进行建模。然而,这些方法受到 TransE 在处理 N-1 关系方面的限制以及单个分类任务的狭窄范围(即仅检测欺诈者)。在本文中,我们将评论系统建模为异构信息网络(HIN),它能够为每个组件提供唯一的表示,并通过聚合附近节点的特征对评论数据执行图归纳学习。具有图归纳功能的 HIN 有助于解决伪装问题(具有真实评论的欺诈者),当与冷启动(即具有真实首次评论的新欺诈者)结合使用时,该问题会变得更加严重。在这项研究中,不是只关注一个组件,检测欺诈评论或欺诈用户(欺诈者),而是学习每个组件的向量表示,从而实现多组件分类。换句话说,我们可以检测欺诈评论、欺诈者和欺诈目标商品,因此我们的方法被称为 DFraud3。 DFraud3 的准确度比 Yelp 上最先进的技术显着提高了 13%。
更新日期:2021-05-19
down
wechat
bug