Trailblazing the Artificial Intelligence for Cybersecurity Discipline: A Multi-Disciplinary Research Roadmap
Trailblazing the Artificial Intelligence for Cybersecurity Discipline: A Multi-Disciplinary Research Roadmap
复制标题
DOI：
10.1145/3430360
复制
发表时间：
2020-12-01
影响因子：
2.5
通讯作者：
Chen, Hsinchun
中科院分区：
文献类型：
--
作者：
Samtani, Sagar;Kantarcioglu, Murat;Chen, Hsinchun
网络安全已迅速成为21世纪世纪的重大社会挑战。积极应对新出现的网络安全挑战的创新解决方案对于确保安全和有保障的社会至关重要。人工智能（AI）已迅速成为筛选TB级异构网络安全数据的可行方法，以前所未有的效率和有效性执行基本网络安全任务，如资产优先级排序、控制分配、漏洞管理和威胁检测。尽管人工智能和网络安全最初有希望，但它们传统上是依赖于不同知识和方法的孤立学科。因此，AI for Cybersecurity学科处于起步阶段。在本文中，我们的目标是为网络安全学科的AI发展提供重要的一步。我们首先概述了当前的网络安全数据，总结了网络安全应用领域的现有人工智能，并确定了当前环境中的关键限制。基于这些关键问题，我们提供了一个多学科人工智能网络安全路线图，该路线图以网络安全应用程序和数据、网络安全高级人工智能方法论以及人工智能决策等主要主题为中心。为了帮助学者和从业者在解决这些重大的人工智能网络安全问题方面取得重大进展，我们总结了美国国家科学基金会（NSF）有前途的资助机制，这些机制可以支持长期，系统的研究计划。最后，我们将介绍这期特刊中的文章。
Cybersecurity has rapidly emerged as a grand societal challenge of the 21st century. Innovative solutions to proactively tackle emerging cybersecurity challenges are essential to ensuring a safe and secure society. Artificial Intelligence (AI) has rapidly emerged as a viable approach for sifting through terabytes of heterogeneous cybersecurity data to execute fundamental cybersecurity tasks, such as asset prioritization, control allocation, vulnerability management, and threat detection, with unprecedented efficiency and effectiveness. Despite its initial promise, AI and cybersecurity have been traditionally siloed disciplines that relied on disparate knowledge and methodologies. Consequently, the AI for Cybersecurity discipline is in its nascency. In this article, we aim to provide an important step to progress the AI for Cybersecurity discipline. We first provide an overview of prevailing cybersecurity data, summarize extant AI for Cybersecurity application areas, and identify key limitations in the prevailing landscape. Based on these key issues, we offer a multi-disciplinary AI for Cybersecurity roadmap that centers on major themes such as cybersecurity applications and data, advanced AI methodologies for cybersecurity, and AI-enabled decision making. To help scholars and practitioners make significant headway in tackling these grand AI for Cybersecurity issues, we summarize promising funding mechanisms from the National Science Foundation (NSF) that can support long-term, systematic research programs. We conclude this article with an introduction of the articles included in this special issue.