D-ISN: TRACK 1: Collaborative Research: Discovery, Analysis, and Disruption of Illicit Narcotic Supply Networks

D-ISN：轨道 1：协作研究：非法麻醉品供应网络的发现、分析和破坏

• 批准号: 2039862
• 负责人: Subramanian Raghavan
• 金额: $ 74.38万
• 依托单位: University of Maryland, College Park
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2025-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2039862&HistoricalAwards=false
• 关键词: ISN; TRACK; Collaborative; Research; Discovery

As transnational drug cartels continue to grow in size and scope, their trafficking networks have become more complex and fragmented. This Disrupting Operations of Illicit Supply Networks (D-ISN) project takes a multi-disciplinary, scientific approach to build better insight and optimization of counter-narcotics efforts in the United States. It refines analytic methods to develop an understanding of the network structure and models of the flow of cocaine, which supports disruption strategies of anti-narcotics and other law enforcement agencies.The project analyzes the dynamics of narcotic supply networks and how interdiction strategies disrupt these networks. Employing a convergent approach that combines operations research, computer science, criminology, public policy, geographic, and economic perspectives, this research exploits network analysis of temporal and spatial cocaine price data to infer illicit supply chain network structure and flow. Artificial intelligence and learning models are applied on the empirical data to extract network behavior in response to interdiction activities, while game theoretic models blend combinatorial optimization and agent-based simulation to evaluate the outcomes of various interdiction strategies. Results will be integrated into a network optimization model to explain the structure of illicit drug supply chains and provide evidence to support successful disruption strategies.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.

随着跨国毒品卡特尔的规模和范围不断增长，他们的贩运网络变得更加复杂和分散。非法供应网络（D-ISN）项目的这种破坏性操作采用了多学科的科学方法，以建立更好的洞察力并优化美国的反毒品工作。它完善了分析方法，以发展对可卡因流动的网络结构和模型的理解，该方法支持反毒品和其他执法机构的破坏策略。该项目分析了麻醉供应网络的动态以及拦截策略如何破坏这些网络。该研究采用了合并运营研究，计算机科学，犯罪学，地理和经济观点的收敛方法，该研究利用了时间和空间可卡因价格数据的网络分析，以推断非法供应链网络结构和流动。人工智能和学习模型应用于经验数据上，以响应构件活动来提取网络行为，而游戏理论模型混合组合组合优化和基于代理的仿真来评估各种插入策略的结果。结果将集成到网络优化模型中，以解释非法药物供应链的结构，并提供证据以支持成功的破坏策略。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的知识分子和更广泛影响的评估评估来获得支持的。

项目成果

Analyzing Illegal Psychostimulant Trafficking Networks Using Noisy and Sparse Data

使用嘈杂和稀疏的数据分析非法精神兴奋剂贩运网络

• DOI: 10.1080/24725854.2023.2254357
• 发表时间: 2023
• 期刊: IISE Transactions
• 影响因子: 2.6
• 作者: Bjarnadottir, Margret V.;Chandra, Siddharth;He, Pengfei;Midgette, Greg
• 通讯作者: Midgette, Greg

Learning Revenue-Maximizing Auctions With Differentiable Matching

• 发表时间: 2021-06
• 期刊: ArXiv
• 作者: Michael J. Curry;Uro Lyi;T. Goldstein;John P. Dickerson

Planning to Fairly Allocate: Probabilistic Fairness in the Restless Bandit Setting

规划公平分配：不安定强盗环境中的概率公平

• DOI: 10.1145/3580305.3599467
• 发表时间: 2023
• 期刊: KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
• 作者: Herlihy, Christine;Prins, Aviva;Srinivasan, Aravind;Dickerson, John P.
• 通讯作者: Dickerson, John P.

Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments

• DOI: 10.48550/arxiv.2205.07015
• 发表时间: 2022-05
• 期刊: ArXiv
• 作者: Ryan Sullivan;J. K. Terry;Benjamin Black;John P. Dickerson

The Dichotomous Affiliate Stable Matching Problem: Approval-Based Matching with Applicant-Employer Relations

• DOI: 10.24963/ijcai.2022/51
• 发表时间: 2022-02
• 期刊: ArXiv
• 作者: Marina Knittel;Samuel Dooley;John P. Dickerson