EAGER: SaTC-EDU: Discovery, Analysis, Research and Exploration Based Experiential Learning Platform Integrating Artificial Intelligence and Cybersecurity

EAGER：SaTC-EDU：基于发现、分析、研究和探索的体验式学习平台，融合人工智能和网络安全

• 批准号: 2039583
• 负责人: Danda Rawat
• 金额: $ 30万
• 依托单位: Howard University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-01 至 2023-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2039583&HistoricalAwards=false
• 关键词: EAGER; SaTC; EDU; Discovery; Analysis

Machine learning (ML) algorithms and artificial intelligence (AI) systems have already had an immense impact on our society. Lately, AI has been shown to be able to create machine cognition comparable to or even better than human cognition for some applications. AI is also regarded to achieve cybersecurity (i.e., AI for cybersecurity) such as by detecting anomalies, adapting security parameters based on ongoing cyber-attacks, and reacting in real-time to combat cyber-adversaries. However, ML algorithms and AI systems can be controlled, dodged, biased, and misled through flawed learning models and input data. Therefore, ML and AI need robust security and correctness (i.e., cybersecurity for AI) to permit fair and trustworthy AI. Unfortunately, AI and cybersecurity have been treated as two different domains and are not taught as cross-cutting technologies. The primary goal of this project is to explore, develop and integrate a scalable instructional approach for AI-driven cybersecurity and cybersecurity for AI in undergraduate and graduate curricula. This will be accomplished by creating a "learning by doing" environment to address emerging AI and cybersecurity issues that are not covered in an integrated way, if at all, in traditional curricula. This project will help to train the next-generation STEM workforce with knowledge of integrated cybersecurity and AI that will help not only to meet evolving demands of the US government and industries but also to improve the nation’s economic security and preparedness. The core scientific contributions of the proposed research effort will be the development and enhancement of integrated AI and cybersecurity education and research programs at Howard University by leveraging the proposed Discovery, Analysis, Research and Exploration (DARE-AI) -based experiential learning platform to address emerging issues and challenges. The project team proposes to design, develop, use, and refine reproducible hands-on activities by integrating cybersecurity and AI education and research with open-ended problem-solving activities. The effectiveness of coupling of AI for cybersecurity and cybersecurity for AI in DARE-AI modules will be evaluated. The project team will also design, develop, use, and refine the machine learning model with privacy, security, and distributed learning. Machine learning algorithms and AI systems will be designed, developed, and analyzed for robustness, fairness and the extent to which they make AI systems explainable and accountable. The research results from this project will be disseminated through peer-reviewed publications and presentations. The DARE-AI modules will also be published on the project’s dedicated website to make them available to the public.This project is supported by a special initiative of the Secure and Trustworthy Cyberspace (SaTC) program to foster new, previously unexplored, collaborations between the fields of cybersecurity, artificial intelligence, and education. The SaTC program aligns with the Federal Cybersecurity Research and Development Strategic Plan and the National Privacy Research Strategy to protect and preserve the growing social and economic benefits of cyber systems while ensuring security and privacy.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.

机器学习（ML）算法和人工智能（AI）系统已经对我们的社会产生了巨大的影响。最近，人工智能已经被证明能够在某些应用中创建与人类认知相当甚至更好的机器认知。人工智能也被认为是实现网络安全（即，人工智能网络安全），例如通过检测异常，根据正在进行的网络攻击调整安全参数，并实时做出反应以打击网络对手。然而，机器学习算法和人工智能系统可以通过有缺陷的学习模型和输入数据来控制、回避、偏见和误导。因此，ML和AI需要强大的安全性和正确性（即，人工智能的网络安全）允许公平和可信的人工智能。不幸的是，人工智能和网络安全一直被视为两个不同的领域，并没有作为交叉技术进行教学。该项目的主要目标是探索，开发和整合一种可扩展的教学方法，用于本科和研究生课程中的AI驱动的网络安全和AI网络安全。 这将通过创造一个“边做边学”的环境来实现，以解决传统课程中没有综合涵盖的新兴人工智能和网络安全问题。该项目将有助于培训下一代STEM劳动力，掌握集成网络安全和人工智能知识，不仅有助于满足美国政府和行业不断变化的需求，还有助于改善国家的经济安全和准备。拟议研究工作的核心科学贡献将是通过利用拟议的基于发现、分析、研究和探索（DARE-AI）的体验式学习平台，在霍华德大学开发和加强综合人工智能和网络安全教育和研究项目，以解决新出现的问题和挑战。项目团队建议通过将网络安全和人工智能教育与研究与开放式问题解决活动相结合，设计，开发，使用和改进可重复的实践活动。将评估DARE-AI模块中AI网络安全和AI网络安全耦合的有效性。 项目团队还将设计、开发、使用和完善具有隐私、安全和分布式学习的机器学习模型。 机器学习算法和人工智能系统将被设计、开发和分析，以确保其鲁棒性、公平性以及它们使人工智能系统可解释和可问责的程度。这一项目的研究成果将通过同行评审的出版物和介绍加以传播。DARE-AI模块也将发布在该项目的专用网站上，以供公众使用。该项目由安全和可信赖的网络空间（SaTC）计划的一项特别倡议支持，旨在促进网络安全，人工智能和教育领域之间的新的，以前未探索的合作。SATC计划与联邦网络安全研究和发展战略计划和国家隐私研究战略保持一致，以保护和维护网络系统日益增长的社会和经济效益，同时确保安全和隐私。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值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

On the performance of machine learning fairness in image classification

• DOI: 10.1117/12.2665725
• 发表时间: 2023-06
• 作者: Utsab Khakurel;D. Rawat

Evaluating explainable artificial intelligence (XAI): algorithmic explanations for transparency and trustworthiness of ML algorithms and AI systems

评估可解释人工智能 (XAI)：机器学习算法和人工智能系统透明度和可信度的算法解释

• DOI: 10.1117/12.2620598
• 发表时间: 2022
• 期刊: Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications IV
• 作者: Khakurel, Utsab B.;Rawat, Danda B.
• 通讯作者: Rawat, Danda B.

Privacy Preserving Misbehavior Detection in IoV Using Federated Machine Learning

• DOI: 10.1109/ccnc49032.2021.9369513
• 发表时间: 2021-01
• 期刊: 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC)
• 作者: Aashma Uprety;D. Rawat;Jiang Li

On the Performance of Machine Learning Models for Anomaly-Based Intelligent Intrusion Detection Systems for the Internet of Things

• DOI: 10.1109/jiot.2021.3103829
• 发表时间: 2022-03-15
• 期刊: IEEE INTERNET OF THINGS JOURNAL
• 影响因子: 10.6
• 作者: Abdelmoumin, Ghada;Rawat, Danda B.;Rahman, Abdul
• 通讯作者: Rahman, Abdul

Real-Time Physical Threat Detection on Edge Data Using Online Learning

使用在线学习对边缘数据进行实时物理威胁检测

• DOI: 10.1109/mce.2023.3256641
• 发表时间: 2023
• 期刊: IEEE Consumer Electronics Magazine
• 影响因子: 4.5
• 作者: Khakurel, Utsab;Rawat, Danda B.
• 通讯作者: Rawat, Danda B.