Scholarlink

The illicit trafficking of cultural artifacts poses a significant challenge to global heritage preservation, with artifacts frequently being stolen, traded, and sold through unregulated markets. Managing and analyzing multi-source archaeological data is essential for tracking and preventing such activities, yet the fragmentation and heterogeneity of available data sources hinder effective monitoring. This paper presents ENIGMA, a unified framework that integrates graph databases and web crawler infrastructures to enhance the detection and investigation of illicit transactions involving cultural goods. The proposed system leverages a graph database schema to model relationships between artifacts, ownership histories, transactions, and locations, facilitating provenance tracking and anomaly detection. Complementing this, AI-powered web crawlers extract and structure data from auction websites, institutional archives, and online marketplaces. Techniques such as Natural Language Processing (NLP) and Named Entity Recognition (NER) are used to classify and tag extracted information, improving data consistency and reliability. By providing a scalable and interoperable digital infrastructure, ENIGMA enhances collaboration among law enforcement agencies, cultural institutions, and policymakers. This work highlights the potential of combining graph-based analytics and automated web monitoring to combat the illicit trade of cultural goods and outlines future research directions in AI-driven artifact detection, cross-border legal harmonization, and real-time monitoring frameworks.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Graph Databases and Crawler Infrastructures as a Common Workspace for the Unified Management of Multi-source Archaeological Data in the Service of Combating Illicit Trafficking of Cultural Goods

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Haris Zacharatos,
  • Neofitos Vlotomas,
  • Charalampos Georgiadis,
  • Petros Patias,
  • Themistocles Roustanis

摘要

The illicit trafficking of cultural artifacts poses a significant challenge to global heritage preservation, with artifacts frequently being stolen, traded, and sold through unregulated markets. Managing and analyzing multi-source archaeological data is essential for tracking and preventing such activities, yet the fragmentation and heterogeneity of available data sources hinder effective monitoring. This paper presents ENIGMA, a unified framework that integrates graph databases and web crawler infrastructures to enhance the detection and investigation of illicit transactions involving cultural goods. The proposed system leverages a graph database schema to model relationships between artifacts, ownership histories, transactions, and locations, facilitating provenance tracking and anomaly detection. Complementing this, AI-powered web crawlers extract and structure data from auction websites, institutional archives, and online marketplaces. Techniques such as Natural Language Processing (NLP) and Named Entity Recognition (NER) are used to classify and tag extracted information, improving data consistency and reliability. By providing a scalable and interoperable digital infrastructure, ENIGMA enhances collaboration among law enforcement agencies, cultural institutions, and policymakers. This work highlights the potential of combining graph-based analytics and automated web monitoring to combat the illicit trade of cultural goods and outlines future research directions in AI-driven artifact detection, cross-border legal harmonization, and real-time monitoring frameworks.