Using Machine Learning to Provide Students with Rapid Feedback during Hands-on Cybersecurity Exercises

使用机器学习在网络安全实践练习中为学生提供快速反馈

• 批准号: 2216492
• 负责人: Richard Weiss
• 金额: $ 16.14万
• 依托单位: Evergreen State College
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-15 至 2025-05-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2216492&HistoricalAwards=false
• 关键词: Using; Machine; Learning; Provide; Students

This project aims to serve the national interest by using machine learning to provide students with timely feedback while completing hands-on cybersecurity exercises. A cyber informed citizenry is a vital part of our national defense strategy. Cybercrime is becoming increasingly sophisticated, and the systems and devices that need security are becoming ever more complex and interconnected. These issues highlight the need to develop programs that enable students to quickly obtain the fundamental skills and knowledge considered essential by cybersecurity experts. Hands-on cybersecurity exercises are known to provide students with basic cybersecurity knowledge, skills, and abilities. To be effective these exercises need to provide students with rapid feedback to prevent them from getting stuck and frustrated. The goal of this project is to use machine learning to monitor students as they work through hands-on cybersecurity exercises and automatically identify when they are getting stuck and frustrated. The students will then be given suggestions to help them to successfully complete the exercise. This project plans to use reinforcement learning to create, test, and deploy a semi-automated rapid hint system. The project intends to develop tools to collect hints directly from student-teacher interactions, which will then be used to teach the system which hints to apply and when. The system will interact with both the teacher and the student by suggesting hints as the system becomes more proficient. The hint system will be integrated into the EDURange platform but will be compatible with other cyberrange platforms such as DeterLab and KYPO. The PI team intends to offer workshops for faculty on how to use EDURange and the hint system. The hint system will collect data that will be analyzed to determine the efficacy of the tool, and to develop new hints and strategies for helping students. The NSF IUSE: EHR Program supports research and development projects to improve the effectiveness of STEM education for all students. Through the Engaged Student Learning track, the program supports the creation, exploration, and implementation of promising practices and tools.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.

该项目旨在通过利用机器学习为学生提供及时的反馈，同时完成网络安全实践练习来服务国家利益。公民拥有网络信息是我们国防战略的重要组成部分。网络犯罪变得越来越复杂，需要安全的系统和设备也变得越来越复杂和相互关联。这些问题凸显了开发课程的必要性，使学生能够快速获得网络安全专家认为必不可少的基本技能和知识。众所周知，网络安全实践练习可以为学生提供基本的网络安全知识、技能和能力。为了有效，这些练习需要为学生提供快速反馈，以防止他们陷入困境和沮丧。该项目的目标是使用机器学习来监控学生进行网络安全实践练习，并自动识别他们何时陷入困境和沮丧。然后，学生将获得建议，帮助他们成功完成练习。该项目计划使用强化学习来创建、测试和部署半自动化快速提示系统。该项目打算开发工具来直接从师生互动中收集提示，然后用这些工具来教导系统应用哪些提示以及何时应用。随着系统变得更加熟练，系统将通过建议提示与老师和学生进行互动。该提示系统将集成到 EDURange 平台中，但也将与 DeterLab 和 KYPO 等其他网络测距平台兼容。 PI 团队打算为教师提供有关如何使用 EDURange 和提示系统的研讨会。提示系统将收集数据，进行分析以确定该工具的功效，并开发新的提示和策略来帮助学生。 NSF IUSE：EHR 计划支持研究和开发项目，以提高所有学生 STEM 教育的有效性。通过参与学生学习轨道，该计划支持有前途的实践和工具的创建、探索和实施。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力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

Hands-On SQL Injection in the Classroom: Lessons Learned

课堂上的 SQL 注入实践：经验教训

• 发表时间: 2022-01
• 期刊: Journal of computing sciences in colleges
• 作者: Mache, J.;Richardson, N.;Greenlaw Rollins, W.;García Morán*, C.;Weiss, R
• 通讯作者: Weiss, R