EAGER: SaTC-EDU: Artificial Intelligence for Cybersecurity Education via a Machine Learning-Enabled Security Knowledge Graph

EAGER：SaTC-EDU：通过机器学习支持的安全知识图进行网络安全教育的人工智能

• 批准号: 2114789
• 负责人: Huan Liu
• 金额: $ 30万
• 依托单位: Arizona State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-05-01 至 2024-04-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2114789&HistoricalAwards=false
• 关键词: EAGER; SaTC; EDU; Artificial; Intelligence

Cybersecurity education is exceptionally challenging because its learning outcomes often comprise fragmented information that fails to provide learners with adaptive guidance on how to connect and build on the concepts they have learned. This project will develop an artificial intelligence (AI)-enabled cybersecurity tool referred to as a knowledge graph (AISecKG) to address this cybersecurity education challenge. Knowledge graphs, widely used by search engines and social networks, integrate data and can store linked descriptions of items such as objects, concepts, and events. This project applies a novel learning approach for cybersecurity education by providing university students a flexible learning plan that enhances their critical thinking and problem-solving skills. This approach aims to help students understand the complex nature of cyber-attacks and defense mechanisms, provide them with a holistic view and better prepare them to address the complexities of real-world scenarios. The development and deployment of AISecKG are interdisciplinary. First, the project employs machine learning (ML) and AI approaches to build a new cybersecurity knowledge graph by measuring and setting up similarities and dependencies among cybersecurity learning targets for both study planning and learning-outcome assessment. Second, it incorporates a multi-level assessment approach to design cybersecurity curricula, scaffold student cognitive engagement, and improve student learning outcomes. AISecKG has two primary design goals. First, it will guide instructors to develop a problem-based learning curriculum based on their learning objectives. Second, it will allow students to apply an adaptive learning strategy, incorporating hands-on labs to assess their learning outcomes. To assess students’ learning performance quantitatively, AISecKG will (a) deploy an evidence-based model and learning materials for problem-based cybersecurity education focusing on developing teacher capacity and practice while using targeted materials and approaches; (b) produce a productive teaching model for deep learning that promotes a culture of scientific inquiry and design as well as a set of strategies to develop student competency; and (c) provide evidence of student learning outcomes as a pedagogical resource to support student cognitive engagement in learning tasks interactively. This project is supported by a special initiative of the Secure and Trustworthy Cyberspace (SaTC) program to foster new, previously unexplored, collaborations between the fields of cybersecurity, artificial intelligence, and education. The SaTC program aligns with the Federal Cybersecurity Research and Development Strategic Plan and the National Privacy Research Strategy to protect and preserve the growing social and economic benefits of cyber systems while ensuring security and privacy.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.

网络安全教育非常具有挑战性，因为它的学习成果往往包含碎片化的信息，无法为学习者提供如何连接和构建所学概念的适应性指导。该项目将开发一种支持人工智能（AI）的网络安全工具，称为知识图谱（AISecKG），以应对这一网络安全教育挑战。知识图谱被搜索引擎和社交网络广泛使用，它可以整合数据，并存储对象、概念和事件等项目的链接描述。该项目通过为大学生提供灵活的学习计划，提高他们的批判性思维和解决问题的能力，为网络安全教育应用了一种新颖的学习方法。这种方法旨在帮助学生理解网络攻击和防御机制的复杂性，为他们提供一个整体的观点，并更好地为他们应对现实世界场景的复杂性做好准备。AISecKG的开发和部署是跨学科的。首先，该项目采用机器学习（ML）和人工智能方法，通过测量和设置网络安全学习目标之间的相似性和依赖性，构建新的网络安全知识图谱，用于学习计划和学习成果评估。其次，它结合了多层次的评估方法来设计网络安全课程，支撑学生的认知参与，并改善学生的学习成果。AISecKG有两个主要的设计目标。首先，它将指导教师根据自己的学习目标制定基于问题的学习课程。其次，它将允许学生应用适应性学习策略，结合动手实验来评估他们的学习成果。为了定量评估学生的学习表现，AISecKG将(a)部署基于问题的网络安全教育的循证模型和学习材料，重点是在使用目标材料和方法的同时培养教师的能力和实践；(b)为深度学习建立一个富有成效的教学模式，促进科学探究和设计的文化，以及一套培养学生能力的策略；(c)提供学生学习成果的证据，作为一种教学资源，以支持学生在学习任务中的认知互动。该项目由安全与可信网络空间（SaTC）计划的一项特别倡议支持，旨在促进网络安全、人工智能和教育领域之间前所未有的合作。SaTC项目与《联邦网络安全研究与发展战略计划》和《国家隐私研究战略》保持一致，旨在保护和维护网络系统日益增长的社会和经济效益，同时确保安全和隐私。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

Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey

• DOI: 10.48550/arxiv.2311.07914
• 发表时间: 2023-11
• 期刊: ArXiv
• 作者: Garima Agrawal;Tharindu Kumarage;Zeyad Alghami;Huanmin Liu

Development and Validation of the Uncertainty Management in Problem-Based Learning Scale in Postsecondary STEM Education

中学后 STEM 教育中基于问题的学习量表的不确定性管理的开发和验证

• 发表时间: 2023
• 期刊: Annual Meeting of the American Educational Research Association 2023.
• 作者: Park, Jongchan;Deng Yuli;Agrawal Garima;Techawitthayachinda Ratrapee;Chen Ying-Chih;Huang Dijiang;Liu Huan.
• 通讯作者: Liu Huan.

Problems of Problem-Based Learning: Exploring Meta-Agency in Problem-Based Cybersecurity Learning in College Education

基于问题的学习的问题：探索大学教育中基于问题的网络安全学习的元代理

• 发表时间: 2023
• 期刊: Annual Meeting of the American Educational Research Association 2023
• 作者: Park, Jongchan;Deng Yuli;Agrawal Garima;Techawitthayachinda Ratrapee;Chen Ying-Chih;Huang Dijiang;Liu Huan
• 通讯作者: Liu Huan

AISecKG: Knowledge Graph Dataset for Cybersecurity Education

AISecKG：网络安全教育知识图数据集

• 发表时间: 2023
• 期刊: AAAI-MAKE 2023: Challenges Requiring the Combination of Machine Learning 2023
• 作者: Agrawal, Garima

Building Knowledge Graphs from Unstructured Texts: Applications and Impact Analyses in Cybersecurity Education

• DOI: 10.3390/info13110526
• 发表时间: 2022-11
• 期刊: Inf.
• 作者: Garima Agrawal;Yuli Deng;Jongchan Park;Huanmin Liu;Yingying Chen