Metagraph Aggregated Heterogeneous Graph Neural Network for Illicit Traded Product Identification in Underground Market
Metagraph Aggregated Heterogeneous Graph Neural Network for Illicit Traded Product Identification in Underground Market
复制标题
DOI：
10.1109/icdm50108.2020.00022
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Yujie Fan;Yanfang Ye;Qian Peng;Jianfei Zhang;Yiming Zhang-;Xusheng Xiao;C. Shi;Qi Xiong;Fudong Sh
中科院分区：
文献类型：
--
作者：
Yujie Fan;Yanfang Ye;Qian Peng;Jianfei Zhang;Yiming Zhang-;Xusheng Xiao;C. Shi;Qi Xiong;Fudong Sh
新兴的地下市场（例如，黑客论坛）被网络犯罪分子广泛用于非法产品或服务的交易，这在网络犯罪生态系统中发挥了至关重要的作用。为了打击不断发展的网络犯罪，在本文中，我们提出并开发了一个智能框架（名为PIdentifier），以自动分析黑客论坛，用于在第一次尝试时识别私人合同中交易的非法产品（为了逃避执法，卖方和买方之间签订了私人合同，其中交易的产品及其细节是不可见的）。在PIdentifier中，基于Hack Forums复杂生态系统中大规模提取的用户配置文件、用户帖子和不同类型的关系，我们首先引入属性异构信息网络（AHIN）来建模多类型实体之间的丰富语义和复杂关系（即，供应商、买家、产品、评论和主题）。然后，我们设计了不同的元图，制定买家和产品之间的相关性的基础上，提出了一个元聚集异构图神经网络（表示为mHGNN）学习节点表示的非法交易产品识别通过用心传播和聚合的邻域信息所定义的设计的元图。在Hack Forums收集的真实世界数据集上进行了全面的实验。通过与最先进的基线进行比较，令人鼓舞的结果表明了我们提出的PIdentifier框架在非法贸易产品识别方面的性能。
The emerging underground markets (e.g., Hack Forums) have been widely used by cybercriminals to trade in illicit products or services, which have played a vital role in the cybercriminal ecosystem. In order to combat the evolving cybercrimes, in this paper, we propose and develop an intelligent framework (named PIdentifier) to automate the analysis of Hack Forums for the identification of illicit product traded in a private contract at the first attempt (to evade the law enforcement, a private contract is made between a vendor and a buyer where the traded product and its detail are invisible). In PIdentifier, based on the large-scale extracted user profiles, user posts and different types of relations within the complex ecosystem in Hack Forums, we first introduce an attributed heterogeneous information network (AHIN) to model the rich semantics and complex relations among multi-typed entities (i.e., vendors, buyers, products, comments and topics). Then, we design different metagraphs to formulate the relatedness between buyers and products based on which a metagraph aggregated heterogeneous graph neural network (denoted as mHGNN) is proposed to learn node representations for illicit traded product identification by attentively propagating and aggregating the neighborhood information defined by the designed metagraphs. Comprehensive experiments are conducted on the real-world dataset collected from Hack Forums. Promising results demonstrate the performance of our proposed PIdentifier framework in illicit traded product identification by comparison with the state-of-the-art baselines.