D-ISN/​Collaborative Research: An Interdisciplinary Approach to the Discovery, Analysis, and Disruption of Wildlife Trafficking Networks

这个名为“打击非法供应网络行动”（D-ISN）的项目旨在解决野生动物的非法贸易问题。野生动物贩运是全球最常见的非法活动之一，造成了巨大的人类成本以及有害的社会和经济影响，包括犯罪、暴力和环境破坏的增加。2019冠状病毒病大流行可能是由一种病毒从野生动物市场传播给人类造成的，这表明野生动物贩运可能对公共卫生和生物安全产生严重影响。该项目旨在通过创建工具来促进技术创新，使领域专家能够通过探索分布在多个来源的与非法网络有关的大量数据，不断发现并获得可操作的见解。该项目将通过数据发现、分析和建模的新方法，提高我国打击野生动物贩运活动的能力。该项目还将促进对网络犯罪活动的研究进展。在项目过程中收集的数据将通过数据集搜索引擎公开，使研究人员能够通过动态发现和链接以前未知的数据来丰富数据驱动的分析，并允许他们回答重要问题。项目小组与非政府组织的合作以及与执法机构的讨论将促进互动进程，从而能够调整干扰技术并提出务实的实际执行战略和政策建议。该项目采用跨学科方法，将计算机科学和工程以及野生动物犯罪学的方法和工具结合起来，推动最新技术的发展，并在发现和探索与在线足迹有关的非法活动数据的方法方面建立基础知识，同时加强野生动物贩运研究。具体而言，该项目提供了新的算法，提供以下能力：1)以前所未有的规模从多个平台发现和自动收集与野生动物贩运有关的数据；2)利用这些数据建立计算模型，研究全球范围内的野生动物贩运模式和网络。通过使用犯罪地图、定量数据分析和社会网络分析等分析技术，该项目将解决与非法野生动物贸易的规模和性质、在线野生动物贩运的网络结构以及可用于最佳解决这些问题的经验驱动的中断模型相关的研究问题。这些算法适用于不同的领域和数据，支持非结构化数据和结构化数据集的发现，并将作为可用工具的基础，使领域专家能够持续发现和监控相关数据。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This Disrupting Operations of Illicit Supply Networks (D-ISN) project aims to address the illegal trade in wild animals. Wildlife trafficking is one of the most common illicit activities globally and poses a substantial human cost along with detrimental social and economic impacts, including increased crime, violence, and environmental destruction. The COVID-19 pandemic, likely the result of a virus that spread to humans from a wildlife market, demonstrates that wildlife trafficking can have serious public health and biosafety implications. This project seeks to catalyze technological innovations by creating tools that empower domain experts to continuously discover and obtain actionable insights by exploring the wealth of data related to illicit networks that spread over multiple sources. The project will advance our Nation's ability to counter wildlife trafficking activities through novel approaches for data discovery, analytics, and modeling. The project will also promote the progress of research in criminal activities that have an online footprint. Data collected in the course of the project will be made publicly available through a dataset search engine, making it possible for researchers to enrich data-driven analyses through the dynamic discovery and linkage of previously unknown data, and allowing them to answer important questions. The project team's collaboration with non-governmental organizations and discussions with law enforcement agencies will facilitate an interactive process that can fine-tune disruption techniques and suggest pragmatic real-world implementation strategies and policy recommendations.The project uses an interdisciplinary approach – combining methods and tools from computer science and engineering as well as wildlife criminology to advance the state of the art and build fundamental knowledge in methods for the discovery and exploration of data related to illicit activities with an online footprint, as well as enhance wildlife trafficking research. Specifically, this project contributes new algorithms that provide capabilities to: 1) discover and automatically collect data related to wildlife trafficking from multiple platforms at an unprecedented scale; and 2) use these data to build computational models and study wildlife trafficking patterns and networks at the global level. Through the use of analytical techniques such as crime mapping, quantitative data analysis, and social network analysis, this project will address research questions related to the scale and the nature of illicit wildlife trade, network structures of online wildlife trafficking, and empirically-driven disruption models that can be used to best tackle them. The algorithms are adaptable to different domains and data, support the discovery of both unstructured data and structured datasets, and will serve as the basis for usable tools that empower domain experts to continuously discover and monitor relevant data.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.