skip to main content

Title: Trailblazing the Artificial Intelligence for Cybersecurity Discipline: A Multi-Disciplinary Research Roadmap
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.  more » « less
Award ID(s):
1917117 2038483 1936370
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
ACM Transactions on Management Information Systems
Page Range / eLocation ID:
1 to 19
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Generative AI is rapidly transforming the frontier of research in computational structural biology. Indeed, recent successes have substantially advanced protein design and drug discovery. One of the key methodologies underlying these advances is diffusion models (DM). Diffusion models originated in computer vision, rapidly taking over image generation and offering superior quality and performance. These models were subsequently extended and modified for uses in other areas including computational structural biology. DMs are well equipped to model high dimensional, geometric data while exploiting key strengths of deep learning. In structural biology, for example, they have achieved state‐of‐the‐art results on protein 3D structure generation and small molecule docking. This review covers the basics of diffusion models, associated modeling choices regarding molecular representations, generation capabilities, prevailing heuristics, as well as key limitations and forthcoming refinements. We also provide best practices around evaluation procedures to help establish rigorous benchmarking and evaluation. The review is intended to provide a fresh view into the state‐of‐the‐art as well as highlight its potentials and current challenges of recent generative techniques in computational structural biology.

    This article is categorized under:

    Data Science > Artificial Intelligence/Machine Learning

    Structure and Mechanism > Molecular Structures

    Software > Molecular Modeling

    more » « less
  2. Artificial Intelligence (AI) and cybersecurity are becoming increasingly intertwined, with AI and Machine Learning (AI/ML) being leveraged for cybersecurity, and cybersecurity helping address issues caused by AI. The goal in our exploratory curricular initiative is to dovetail the need to teach these two critical, emerging topics in highschool, and create a suite of novel activities, 'AI & Cybersecurity for Teens' (ACT) that introduces AI/ML in the context of cybersecurity and prepares high school teachers to integrate them in their cybersecurity curricula. Additionally, ACT activities are designed such that teachers (and students) build a deeper understanding of how ML works and how the machine actually "learns". Such understanding will aid more meaningful interrogation of critical issues such as AI ethics and bias. ACT introduces core ML topics contextualized in cybersecurity topics through a range of programming activities and pre-programmed games in NetsBlox, an easy-to-use block-based programming environment. We conducted 2 pilot workshops with 12 high school cybersecurity teachers focused on ACT activities. Teachers' feedback was positive and encouraging but also highlighted potential challenges in implementing ACT in the classroom. This paper reports on our approach and activities design, and teachers' experiences and feedback on integrating AI into high school cybersecurity curricula. 
    more » « less
  3. null (Ed.)
    Glasses have been an integral part of human life for more than 2000 years. Despite several years of research and analysis, some fundamental and practical questions on glasses still remain unanswered. While most of the earlier approaches were based on (i) expert knowledge and intuition, (ii) Edisonian trial and error, or (iii) physics-driven modeling and analysis, recent studies suggest that data-driven techniques, such as artificial intelligence (AI) and machine learning (ML), can provide fresh perspectives to tackle some of these questions. In this article, we identify 21 grand challenges in glass science, the solutions of which are either enabling AI and ML or enabled by AI and ML to accelerate the field of glass science. The challenges presented here range from fundamental questions related to glass formation and composition–processing–property relationships to industrial problems such as automated flaw detection in glass manufacturing. We believe that the present article will instill enthusiasm among the readers to explore some of the grand challenges outlined here and to discover many more challenges that can advance the field of glass science, engineering, and technology. 
    more » « less
  4. Responsible Data Science (RDS) and Responsible AI (RAI) have emerged as prominent areas of research and practice. Yet, educational materials and methodologies on this important subject still lack. In this paper, I will recount my experience in developing, teaching, and refining a technical course called “Responsible Data Science”, which tackles the issues of ethics in AI, legal compliance, data quality, algorithmic fairness and diversity, transparency of data and algorithms, privacy, and data protection. I will also describe a public education course called “We are AI: Taking Control of Technology” that brings these topics of AI ethics to the general audience in a peer-learning setting. I made all course materials are publicly available online, hoping to inspire others in the community to come together to form a deeper understanding of the pedagogical needs of RDS and RAI, and to develop and share the much-needed concrete educational materials and methodologies. 
    more » « less
  5. Federal funding agencies and industry entities are seeking innovative approaches to address the ever-growing cybersecurity crisis. Increasingly, numerous cybersecurity thought leaders are indicating that Artificial Intelligence (AI)-enabled analytics can help tackle key cybersecurity tasks and deploy defenses. This half-day workshop, co-located with ACM KDD, sought to attain significant research contributions to various aspects of AI-enabled analytics for cybersecurity applications and deployable defense solutions from academics and practitioners. This workshop was a joint workshop of the 2021 AI-enabled Cybersecurity Analytics and 2021 International Workshop on Deployable Machine Learning for Security Defense. As such, we developed an interdisciplinary Program Committee with significant experience in various aspects of AI, cybersecurity, and/or deployable defense. 
    more » « less