权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Protecting Soft Targets against Lone Actor Attacks using Game Theory and Immersive Simulations

使用博弈论和沉浸式模拟保护软目标免受孤独演员攻击

基本信息

批准号：
1901721
负责人：
Melike Baykal-Gursoy
金额：
$ 32.5万
依托单位：
Rutgers University New Brunswick
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2019
资助国家：
美国
起止时间：
2019-08-01 至 2023-07-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1901721&HistoricalAwards=false
关键词：
Protecting Soft Targets against Lone

项目摘要

This project examines terrorist attacks by individuals who are outside of an organized terrorist group (lone actor attackers) that target public spaces like train stations (soft targets). Such attacks have increased 134 percent in the last 20 years, yet lone actor attack-defend models have not kept up with the trend. The project will develop new models based on game-theory to understand attack and defense strategies combined with immersive simulations that can validate the theoretical models. The project team has expertise in the fields of operations research, industrial and systems engineering, psychology, and electrical and computer engineering. Implementation of this work will contribute to the national priority to reduce risk to critical infrastructures and their users. Furthermore, it will provide advanced training in game-theoretic models for undergraduate and graduate students. This scientific research contribution thus supports NSF's mission to promote the progress of science and to advance our national welfare. In this case, the benefits will be insights to improve man-made emergency management, which can save lives in future events.This project addresses the gaps in current understanding of lone actor attacks to guide the development of new innovative defense strategies. Specific research objectives are: 1) to develop and analyze game-theoretic models of attack and defense strategies, and protection algorithms, to be used by the defenders against lone actor attackers; 2) to design immersive simulations to provide descriptive agents' behavior and to validate the game-theoretic models using risk metrics such as expected damage, and the fraction of unsuccessful attacks. The intellectual merit of this research is the broadening of the knowledge base of game theory with incomplete information, multi-agent (attacker and defender) learning, and stochastic games of partially observable systems. This is transformational research since it brings a fresh vision into the risk management, immersive simulations, statistical learning and normative behavior studies for infrastructure security. The anticipated results of this research are both analytical and practical for emergency management agencies, transportation safety officers, and the police.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.

该项目研究了有组织恐怖组织之外的个人（单独行动者攻击者）针对公共场所（如火车站）的恐怖袭击（软目标）。在过去的20年里，这类攻击增加了134%，但单独行动的攻击防御模式并没有跟上这一趋势。该项目将开发基于博弈论的新模型，以了解攻击和防御策略，并结合可验证理论模型的沉浸式模拟。项目团队在运筹学、工业和系统工程、心理学、电子和计算机工程等领域拥有专业知识。这项工作的实施将有助于减少对关键基础设施及其用户的风险的国家优先事项。此外，它将为本科生和研究生提供博弈论模型的高级培训。这一科研贡献支持了NSF促进科学进步和提高国家福利的使命。在这种情况下，好处将是改进人为应急管理的见解，这可以在未来的事件中挽救生命。该项目解决了目前对单独行动者攻击的理解差距，以指导新的创新防御战略的发展。具体的研究目标是：1)开发和分析攻击和防御策略的博弈论模型和保护算法，供防御者用于对抗单独行动者攻击者；2)设计沉浸式模拟，提供描述性代理的行为，并使用预期损害和攻击失败比例等风险指标验证博弈论模型。本研究的智力价值在于拓宽了不完全信息博弈论、多智能体（攻击者和防御者）学习和部分可观察系统随机博弈的知识库。这是一项变革性的研究，因为它为基础设施安全的风险管理、沉浸式模拟、统计学习和规范行为研究带来了新的视角。本研究的预期结果对应急管理机构、交通安全官员和警察具有分析性和实用性。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。

项目成果

期刊论文数量（12）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

A Cooperative Jamming Game in Wireless Networks Under Uncertainty

DOI：
10.1007/978-3-030-63086-7_14
发表时间：
2020-10
期刊：
影响因子：
0
作者：
Zhifan Xu;M. Baykal-Gursoy
通讯作者：
Zhifan Xu;M. Baykal-Gursoy

A decomposable resource allocation model with generalized overarching protections

DOI：
10.1007/s10479-022-05064-w
发表时间：
2022-11
期刊：
Annals of Operations Research
影响因子：
4.8
作者：
A. Yolmeh;M. Baykal-Gürsoy;V. Bier
通讯作者：
A. Yolmeh;M. Baykal-Gürsoy;V. Bier

Efficient Network Protection Games Against Multiple Types Of Strategic Attackers

DOI：
10.1109/icassp39728.2021.9413758
发表时间：
2021-06
期刊：
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子：
0
作者：
Zhifan Xu;M. Baykal-Gursoy
通讯作者：
Zhifan Xu;M. Baykal-Gursoy

Game Data for the Paint Fever game

《Paint Fever》游戏的游戏数据