CCRI: Planning-C: A Community Research Infrastructure for Integrated AI-Enabled Malware and Network Data Analytics

近年来，网络犯罪和网络攻击的严重性、频率、范围和复杂性呈爆炸式增长，给组织造成了巨大的经济损失，并威胁到关键基础设施（例如，能源网、水安全、交通、医疗保健）和我们社会最基本的基础。虽然每个社区的研究人员已经开发和使用了大量用于网络安全和人工智能的开源技术;利用这两种技术来解决网络安全和人工智能交叉点问题的研究机会并没有被网络安全社区和人工智能社区广泛利用，这是由于挑战，例如保护网络数据中的敏感信息，有限的地面实况数据、零日漏洞、规避恶意软件以及处理大量高维网络数据。这个规划-C项目由宾夕法尼亚州立大学、Merit Network和德克萨斯大学阿灵顿分校合作进行，旨在广泛征求网络安全和人工智能研究社区的意见，涉及（1）可以使用人工智能解决的网络安全研究机会，以及（2）研究界无法广泛获得的相关基础设施需求。 规划研讨会的一个混乱输出是在合适的地点生成和发布报告。 该规划项目的结果将确定可以从AI支持的解决方案中受益的关键网络安全问题，以及这些AI支持的网络安全研究的基础设施要求，这些研究尚未被网络安全社区和AI社区广泛访问。在网络安全和人工智能的交叉点上确定这些研究机会和基础设施需求，将加快相关开源软件工具和基础设施的选择、集成和调整，并根据需要创建新工具。 这些工具和基础设施不仅将加速使用人工智能的网络安全解决方案的迫切需要的进步，而且还扩大了早期职业学者和来自STEM代表性不足群体的学生参与这些研究机会，以进一步提高未来的多样性，该奖项反映了NSF的法定使命，并通过使用基金会的学术价值和更广泛的影响审查标准。

The severity, frequency, scope, and sophistication of cybercrimes and cyberattacks have exploded in recent years, which resulted in huge financial damages to organizations, and threatened the critical infrastructures (e.g., energy grid, water safety, transportation, health care) and the most basic foundation of our society. While a host of open-source technologies for cybersecurity and for artificial intelligence have been developed and used by researchers in each community; research opportunities that leverage both of these technologies to tackle problems at the intersection of cybersecurity and artificial intelligence are not broadly accessible to cybersecurity community and AI community due to challenges, such as protection of sensitive information in network data, limited ground truth data, zero-day vulnerabilities, evasive malware, and processing voluminous and high-dimensional network data.This Planning-C project, conducted in collaboration between Pennsylvania State University, Merit Network, and University of Texas at Arlington, aims to broadly solicit inputs from the cyber security and AI research communities regarding (1) research opportunities of cybersecurity that can be addressed using artificial intelligence, and (2) associated infrastructures needs that are not broadly available to the research communities. A tangle output of the planning workshop is to generate and publish a report in a suitable venue. The outcome of this planning project will identify critical cybersecurity problems that can benefit from AI-enabled solutions as well as infrastructure requirements for these AI-enabled cyber security research that are not broadly accessible to the cybersecurity community and the AI community. The identification of these research opportunities and infrastructure needs at the intersection of cybersecurity and artificial intelligence will expedite the selection, integration, and adaptation of relevant open-source software tools and infrastructures, as well as the creation of new tools, as needed. These tools and infrastructures will not only accelerate the critically needed advancement of cyber security solutions using AI, but also broaden the participation of early career scholars and students from under-represented groups in STEM in these research opportunities to further enhance the diversity of next-generation cybersecurity and AI workforce.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.