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不断增长，网络安全研究人员、工程师和从业人员严重依赖先进的网络基础设施 (CI) 技术，例如大数据、机器学习和并行编程，以及先进的 CI 平台，例如云和高性能计算平台。 - 性能计算，用于评估网络风险、识别和减轻威胁并实现纵深防御。然而，先进的 CI 技术尚未在本科生和研究生的网络安全课程中广泛引入。这种缺乏给许多热衷于进行前沿网络安全研究和/或参与先进工业网络安全项目的高年级本科生和早期研究生网络安全学生造成了障碍。该项目推出了一个独特的网络安全研究和教育数据支持高级培训计划 (DeapSECURE)，旨在为本科生和研究生提供先进的 CI 技术，并教他们使用 CI 资源、工具和服务在前沿领域取得成功网络安全研究和工业网络安全项目。该项目满足了汉普顿路大都市区、弗吉尼亚联邦和国家对准备充分的网络安全劳动力的迫切需求。因此，正如 NSF 的使命所述，它服务于国家利益：促进科学进步；促进国民健康、繁荣和福利；该项目开发了六个新的 CI 培训模块，强调先进 CI 技术的实际使用，特别是在网络安全研究背景下实施这些技术的工具。每个培训模块包括三个部分：（1）受邀网络安全教师对其研究进行概述，最后提出一个严重依赖 CI 技术的研究问题； （2）相应的CI技能、工具和平台介绍； (3) 动手实验室课程，学生将应用 CI 技术来解决网络安全教师之前提出的研究问题。这些模块将通过两种不同的方式提供：每月研讨会和暑期学院。学年期间每月举办六个月的研讨会，主要针对奥多明尼恩大学 (ODU) 的学生。暑期学院向来自当地社区学院、ODU 本科生研究经验项目和其他弗吉尼亚大学的学生展示这六个模块；这些活动还包括实地考察、K-12 学生开放日、网络之夜活动、网络安全职业小组和学生竞赛等特殊活动。作为研讨会和暑期学院的补充，我们创建了一个在线持续学习社区，其中包括虚拟计算机实验室和学生论坛，作为学生在面对面课程后继续学习的场所。存档的研讨会材料以及其他学习材料也作为开放教育资源发布在该在线平台上，可供网络安全研究和教育社区使用。学习模块的开源风格开发有利于以有效的方式进行广泛的采用、改编和贡献。该项目利用现有和新的合作伙伴关系来确保广泛参与，并相应扩大先进 CI 技术在网络安全社区的采用。该项目采用了严格的评估和评价计划，该计划植根于各种成功指标，以改进课程并证明其有效性。这些指标基于学生的成绩和毕业调查，由独立评估员进行评估。在培训计划之外采用学习模块也被视为成功的衡量标准。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力优点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

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

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

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

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