Capacity Building: Integrating Data Science into Cybersecurity Curriculum

能力建设：将数据科学融入网络安全课程

• 批准号: 1820685
• 负责人: Edoardo Serra
• 金额: $ 50万
• 依托单位: Boise State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-01 至 2022-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1820685&HistoricalAwards=false
• 关键词: Capacity; Building; Integrating; Data; Science

The project from Boise State University (BSU), a designated Center of Academic Excellence in Cyber Defense Education, proposes to increase the capacity of the United States higher education enterprise to produce security data scientists and cybersecurity professionals with analytic skills. This project seeks to build a capacity in security data science education by integrating data science into a cybersecurity curriculum. This project seeks to address the lack in curriculum materials on security data analytics, and the shortage of faculty that are sufficiently qualified to teach security data science. The materials will blend processes in data sciences, security problems, perspectives of adversaries, and principles of academic course design. Dissemination via an open collaborative repository, faculty development workshops and webinars, presentations and tutorials at professional conferences will open-up pathways for educators around the nation to help them integrate data science topics into their cybersecurity curriculum.The first objective of the project is to develop innovative curriculum materials on security data science by integrating data science workflow, security and privacy problems, the adversary's perspective of security, and inquiry-based learning into hands-on practices. Four self-contained course modules will be created, covering data science for software vulnerability prediction, malicious user detection in social networks, malware detection, and intrusion detection. These modules can be used in existing cybersecurity courses, such as Software Security and Network Security or combined to create a new standalone course on security data analytics. The second objective is to develop an open collaborative repository for the security data science community to host the proposed curriculum materials (e.g., lecture notes, data sets, tools, and lab exercises), and serve the community as a collaborative environment for educators to exchange ideas, contribute new contents, and share resources. The third goal is to hold national faculty development workshops on security data science. The workshops will bring together various stakeholders, such as researchers, educators, industry practitioners, and policy makers, to discuss most recent progresses and needs in security data science and how to integrate data science into specific security courses.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.

该项目来自博伊西州立大学（BSU），该大学是网络防御教育学术卓越中心，旨在提高美国高等教育企业培养具有分析技能的安全数据科学家和网络安全专业人员的能力。该项目旨在通过将数据科学整合到网络安全课程中来建立安全数据科学教育的能力。该项目旨在解决安全数据分析课程材料的缺乏，以及有足够资格教授安全数据科学的教师短缺的问题。这些材料将融合数据科学、安全问题、对手的观点和学术课程设计原则的过程。通过开放的协作知识库、教师发展研讨会和网络研讨会、专业会议上的演示和教程，为全国各地的教育工作者开辟了一条道路，帮助他们将数据科学主题融入网络安全课程。该项目的第一个目标是通过整合数据科学工作流程、安全和隐私问题、对手对安全的看法，以及将基于探究的学习转化为实际操作。将创建四个独立的课程模块，涵盖用于软件漏洞预测的数据科学，社交网络中的恶意用户检测，恶意软件检测和入侵检测。这些模块可用于现有的网络安全课程，如软件安全和网络安全，或结合起来创建一个新的独立的安全数据分析课程。第二个目标是为安全数据科学社区开发一个开放的协作存储库，以托管拟议的课程材料（例如，课堂讲稿、数据集、工具和实验练习），并为社区提供一个协作环境，供教育工作者交流思想、贡献新内容和共享资源。第三个目标是举办关于安全数据科学的国家教师发展研讨会。研讨会将汇集研究人员、教育工作者、行业从业者和政策制定者等各利益相关者，讨论安全数据科学的最新进展和需求，以及如何将数据科学融入特定的安全课程。该奖项反映了NSF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

Identifying ATT&CK Tactics in Android Malware Control Flow Graph Through Graph Representation Learning and Interpretability (Student Abstract)

识别 ATT

• 发表时间: 2022
• 期刊: Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence - Student Abstract and Poster Program
• 作者: Fairbanks, J.;Orbe, A.;Patterson, C.;Serra, E.;Scheepers, M.
• 通讯作者: Scheepers, M.

Modeling Misinformation Diffusion in Social Media: Beyond Network Properties

对社交媒体中的错误信息扩散进行建模：超越网络属性

• DOI: 10.1109/cogmi52975.2021.00030
• 发表时间: 2021
• 作者: Spezzano, Francesca

GAPS: Generality and Precision with Shapley Attribution

GAPS：Shapley 归因的通用性和精确性

• 发表时间: 2022
• 期刊: 2022 {IEEE} International Conference on Big Data (Big Data
• 作者: Daley, Brian;Ratul, Qudrat E;Serra, E.;Cuzzocrea, Alfredo
• 通讯作者: Cuzzocrea, Alfredo

Characterizing and predicting fake news spreaders in social networks

• DOI: 10.1007/s41060-021-00291-z
• 发表时间: 2021-11-22
• 期刊: INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS
• 影响因子: 2.4
• 作者: Shrestha, Anu;Spezzano, Francesca
• 通讯作者: Spezzano, Francesca

Detecting Saturation Attacks in SDN via Machine Learning

• DOI: 10.1109/cccs.2019.8888049
• 发表时间: 2019-10
• 期刊: 2019 4th International Conference on Computing, Communications and Security (ICCCS)
• 作者: Samer Y. Khamaiseh;Edoardo Serra;Zhiyuan Li;Dianxiang Xu