Phase II IUCRC University of North Carolina Charlotte: Center for Cybersecurity Analytics and Automation CCAA

随着网络攻击的规模和复杂性不断增加，网络战已成为国家安全的主要威胁。然而，最先进的网络安全仍然远远没有提供足够的保护，不仅是为互联网企业服务，也是为关键基础设施服务，如金融和能源部门。随着攻击面的指数增长和完全依赖人类的分析和反应，检测和缓解网络攻击的时间显著增加(例如，可能需要长达几个月的时间)。此外，部署网络安全的成本一直在大幅增加，因为它变得非常资源和劳动力密集型。北卡罗来纳大学夏洛特分校(UNC Charlotte)领导着NSF IUCRC网络安全分析和自动化中心(CCAA)的研究和行业社区，以应对这些挑战。我们的目标是建立跨学科学术研究人员、行业合作伙伴和政府机构的临界群体，通过开发自主和自适应网络防御的创新感知和决策能力，促进网络安全分析和自动化的科学和最先进水平，这种能力需要最少的人参与，具有可证明和可测量的安全和弹性特性。我们考虑对网络安全产品进行正式的和数据驱动的分析，以无缝地整合感知和决策，以实现自适应和自主的网络防御。CCAA汇集了形式和数据驱动的网络安全方面的专家，以在多个战线推进网络防御，即(A)使用不同的网络人工制品开发动态和预测性的网络风险分析，(B)根据任务要求和系统配置，为可证明正确和安全的防御战略制定自适应和自主决策，以及(C)将网络弹性和敏捷性作为网络和网络物理系统安全的固有属性。北卡罗来纳大学夏洛特分校将领导研究和管理活动，并在配置验证、自动风险量化和缓解、自适应学习、网络威胁分析和网络敏捷性的正式方法方面为CCAA提供深刻的技术贡献。该中心将创建和维护一个中心范围的储存库，以制造所有研究产品？数据集、代码、工具、实验结果、手稿草稿等？中心所有会员均可参加？S会员。该资料库将通过S中心网站(http://www.ccaa-nsf.org/).)访问是否与中心、S的规章制度及任何适用的国家科学基金会或个别大学保持一致？根据要求，这些产品中的几个将提供给更广泛的研究和行业社区。在第二阶段工作期间，将积极维护该存储库，并可在线访问。该奖项反映了NSF的法定使命，并已通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

With the increasing magnitude and sophistication of cyber attacks, cyber warfare has become a major threat to national security. However, the cybersecurity state of the art is still far from providing sufficient protection, not only for Internet enterprise services but also for critical infrastructure services, such as in the financial and energy sectors. With the exponential increase of attack surface and the complete reliance on human analysis and response, the time for detection and mitigation of cyber attacks have been significantly increasing (e.g., can take up to several months). In addition, the cost of deploying cybersecurity has been tremendously increasing as it is becoming very resource and labor intensive. The University of North Carolina Charlotte (UNC Charlotte) is leading the research and industry community in NSF IUCRC Center on Cybersecurity Analytics and Automation (CCAA) to address these challenges. Our goal is to build the critical mass of inter-disciplinary academic researchers, industry partners, and government agencies for advancing the science and state-of-the-art of cybersecurity analytics and automation by developing innovative sense-making and decision-making capabilities for autonomous and adaptive cyber defense that requires minimal human involvement with provable and measurable security and resiliency properties. We consider both formal- and data-driven analytics of cybersecurity artifacts for seamlessly integrating sense-making and decision-making for adaptive and autonomous cyber defense. CCAA brings together experts in formal and data-driven cybersecurity to advance cyber defense on multiple fronts, namely, (a) developing dynamic and predictive cyber risk analytics using heterogeneous cyber artifacts, (b) developing adaptive and autonomic decision-making for provably correct and safe defense strategies according to the mission requirements, and system configurations and (c) integrating cyber resilience and agility as inherent properties of cyber and cyber-physical system security. The UNC Charlotte site will lead the research and management activities and provides profound technical contributions to CCAA in formal methods for configuration verification, automated risk quantification and mitigation, adaptive learning, cyber threat analytics, and cyber agility. The Center will create and maintain a center-wide repository to make all products of the research ? datasets, code, tools, experimental results, draft manuscripts, etc. ? available to all Center?s members. The repository will be accessible through the Center?s website (http://www.ccaa-nsf.org/). Consistently with the Center?s bylaws and with any applicable NSF or individual universities? requirements, several of these products will be made available to the broader research and industry community. The repository will be actively maintained during the duration of the Phase II effort, and it can be accessed online.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.