CyberTraining:CIC: DeapSECURE: A Data-Enabled Advanced Training Program for Cyber Security Research and Education

Cyber​​Training：CIC：DeapSECURE：用于网络安全研究和教育的数据支持高级培训计划

• 批准号: 1829771
• 负责人: Hongyi Wu
• 金额: $ 50万
• 依托单位: Old Dominion University Research Foundation
• 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=1829771&HistoricalAwards=false
• 关键词: CyberTraining; CIC; DeapSECURE; Data; Enabled

As the volume and sophistication of cyber-attacks grow, cybersecurity researchers, engineers and practitioners heavily rely on advanced cyberinfrastructure (CI) techniques such as big data, machine learning, and parallel programming, as well as advanced CI platforms, e.g., cloud and high-performance computing to assess cyber risks, identify and mitigate threats, and achieve defense in depth. However, advanced CI techniques have not been widely introduced in undergraduate and graduate cybersecurity curricula. This lack creates a hurdle for many senior undergraduates and early-stage graduate cybersecurity students who are keen to conduct cutting-edge cybersecurity research and/or participate in advanced industrial cybersecurity projects. This project introduces a unique Data-Enabled Advanced Training Program for Cyber Security Research and Education (DeapSECURE), aimed to prepare undergraduate and graduate students with advanced CI techniques and teach them to use CI resources, tools, and services to succeed in cutting-edge cybersecurity research and industrial cybersecurity projects. The project responds to the urgent need for well-prepared cybersecurity workforce in the Hampton Roads metropolitan region, the Commonwealth of Virginia, and the Nation. It, thus, serves the national interest, as stated by NSF's mission: to promote the progress of science; to advance the national health, prosperity and welfare; or to secure the national defense.This project develops six new CI training modules which emphasize the practical use of the advanced CI techniques, especially the tools that implement them, in the context of cybersecurity research. Each training module includes three sections: (1) an overview presented by an invited cybersecurity faculty about his/her research, concluding with a research problem that heavily depends on CI techniques; (2) an introduction of corresponding CI skills, tools and platforms; (3) a hands-on lab session where students will apply the CI techniques to solve the research problem formerly introduced by the cybersecurity faculty. The modules will be delivered via two distinct means: monthly workshops and summer institutes. Six monthly workshops are conducted during academic year, primarily targeting students enrolled at Old Dominion University (ODU). The summer institutes present these six modules to students from local community colleges, Research Experiences for Undergraduates program at ODU, and other Virginia universities; they also include special activities such as field trips, open house for K-12 students, Cyber Night events, cybersecurity career panels, and student competitions. Complementing the workshops and summer institutes, an online continuous learning community is created, which includes a virtual computer lab and a student forum, as a place for students to continue their learning engagement after the face-to-face sessions. Archived workshop materials, as well as additional learning materials are also posted on this online platform as open educational resources, to be made available to the cybersecurity research and education communities. The open-source style development of the learning modules facilitates a wide-range of adoption, adaptations, and contributions in an efficient manner. The project leverages existing and new partnerships to ensure broad participation, and accordingly broaden the adoption of advanced CI techniques in the cybersecurity community. The project employs a rigorous assessment and evaluation plan rooted in diverse metrics of success to improve the curricula and demonstrate its effectiveness. The metrics, which are based on the students' outcomes and exit surveys, are assessed by an independent evaluator. The adoption of the learning modules outside of the training program is also considered as a metric of success.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.

随着网络攻击的数量和复杂性的增长，网络安全研究人员，工程师和实践者在很大程度上依赖于高级网络基础设施（CI）技术，例如大数据，机器学习和平行编程，以及高级CI平台，例如，云和高绩效计算来评估网络风险的威胁，并识别较高的风险，并识别识别和MITIGETASS，并识别较高的威胁。但是，在本科和研究生网络安全课程中，尚未广泛引入高级CI技术。这种缺乏为许多热衷于进行最先进的网络安全研究和/或参加高级工业网络安全项目的高级本科生和早期研究生网络安全学生构成了障碍。该项目为网络安全研究和教育（DEAPSECURE）介绍了一项独特的支持数据的高级培训计划，旨在为本科生和研究生提供高级CI技术，并教他们使用CI资源，工具和服务来成功切割边缘网络安全研究和工业网络安全项目。该项目响应汉普顿大都会地区，弗吉尼亚州和国家的迫切需要对网络安全劳动力做好准备的需求。因此，正如NSF的使命所指出的那样：促进科学进步；促进民族健康，繁荣和福利；或为了保护国防部。该项目开发了六个新的CI培训模块，这些模块强调了高级CI技术的实际使用，尤其是在网络安全研究的背景下实施它们的工具。每个培训模块包括三个部分：（1）由受邀网络安全教师提出的有关其研究的概述，最后是一个研究问题，在很大程度上取决于CI技术； （2）引入相应的CI技能，工具和平台； （3）一个动手实验室会议，学生将应用CI技术来解决以前由网络安全教师提出的研究问题。这些模块将通过两种不同的方式交付：每月研讨会和夏季研究所。在学年期间进行六次每月研讨会，主要针对旧自治领大学（ODU）的学生。夏季学院向当地社区大学的学生展示了这六个模块，ODU的本科生研究经验以及其他弗吉尼亚大学；其中还包括特殊活动，例如实地考察，K-12学生开放式旅行，网络夜活动，网络安全职业面板和学生比赛。与研讨会和夏季研究所相辅相成，创建了一个在线连续学习社区，其中包括虚拟计算机实验室和一个学生论坛，作为学生在面对面课后继续学习参与的地方。存档的研讨会材料以及其他学习材料也将在此在线平台上以开放的教育资源发布，可供网络安全研究和教育社区提供。学习模块的开源风格开发促进了广泛的采用，改编和贡献，以有效的方式。该项目利用现有的和新的伙伴关系来确保广泛参与，并因此扩大了网络安全社区中高级CI技术的采用。该项目采用了一项严格的评估和评估计划，该计划植根于成功的多种指标，以改善课程并证明其有效性。基于学生的成果和退出调查的指标由独立评估者评估。培训计划以外的学习模块的采用也被认为是成功的指标。该奖项反映了NSF的法定任务，并被认为是使用基金会的知识分子优点和更广泛的影响审查标准来通过评估来支持的。

项目成果

Hunter: HE-Friendly Structured Pruning for Efficient Privacy-Preserving Deep Learning

• DOI: 10.1145/3488932.3517401
• 发表时间: 2022-05
• 期刊: Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security
• 作者: Yifei Cai;Qiao Zhang;R. Ning;Chunsheng Xin;Hongyi Wu

DeapSECURE Computational Training for Cybersecurity: Progress Toward Widespread Community Adoption

DeapSECURE 网络安全计算培训：社区广泛采用的进展

• 发表时间: 2023
• 期刊: Journal of computational science education
• 作者: Purwanto, Wirawan;Dodge, Bahador;Arcaute, Karina;Sosonkina, Masha;Wu, Hongyi
• 通讯作者: Wu, Hongyi

Hibernated Backdoor: A Mutual Information Empowered Backdoor Attack to Deep Neural Networks

• DOI: 10.1609/aaai.v36i9.21272
• 发表时间: 2022-06
• 作者: R. Ning;Jiang Li;Chunsheng Xin;Hongyi Wu;Chong Wang

TrojanFlow: A Neural Backdoor Attack to Deep Learning-based Network Traffic Classifiers

• DOI: 10.1109/infocom48880.2022.9796878
• 发表时间: 2022-05
• 期刊: IEEE INFOCOM 2022 - IEEE Conference on Computer Communications
• 作者: R. Ning;Chunsheng Xin;Hongyi Wu

CLEAR: Clean-up Sample-Targeted Backdoor in Neural Networks

• DOI: 10.1109/iccv48922.2021.01614
• 发表时间: 2021-10
• 期刊: 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
• 作者: Liuwan Zhu;R. Ning;Chunsheng Xin;Chong Wang;Hongyi Wu