Collaborative Research: SWIFT: SMALL: Understanding and Combating Adversarial Spectrum Learning towards Spectrum-Efficient Wireless Networking

下一代无线网络将是高效、可靠、安全和频谱智能的，以最大限度地提高无线频谱的使用效率。动态频谱接入和管理设计已经显示出其在大幅提高频谱利用效率方面的潜力。在无线网络系统中，为了达到确保高效的频谱访问和利用的目标，收集和使用来自单个节点的频谱报告来检测恶意行为和/或消除攻击影响是很常见的。本项目的目标是了解一种名为对抗频谱学习的新攻击的潜在策略和影响，该攻击旨在从无线频谱数据中学习并构建针对频谱管理系统的特定攻击模型，以破坏网络性能。该项目还将提供对抗对抗频谱学习的有效对策。该项目将通过分析建模、综合模拟和实验评估，重点研究与对抗频谱学习相关的重要研究问题。具体而言，研究小组的目标是：(I)制订恶意攻击可用来扰乱频谱效率的对抗性频谱学习策略，并评估其在不同无线和网络条件下的破坏性影响；(Ii)通过新的非参数检测方法检测对抗性频谱学习攻击；(Iii)创建针对潜在存在对抗性频谱学习的安全和高效频谱接入的攻击预防和安全管理方法；以及(Iv)全面评估拟议检测和预防策略的效率和有效性。该项目的适当元素也将被整合到教育材料中。这一奖项反映了NSF的法定使命，并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。

The next-generation wireless network is expected to be efficient, reliable, secure and spectrum-intelligent to maximize the efficiency of using the wireless spectrum. Dynamic spectrum access and management designs have shown their potential to substantially improve the spectrum utilization efficiency. To achieve the goal of securing efficient spectrum access and utilization, it is common in wireless network systems to collect and use spectrum reports from individual nodes to detect malicious behaviors and/or eliminate attack impacts. The goal of this project is to understand the potential strategies and impacts of a new attack, called adversarial spectrum learning, which aims to learn from the wireless spectrum data and construct specific attack models against spectrum management systems to disrupt the network performance. The project will also provide effective countermeasure against adversarial spectrum learning.The project will focus on studying important research problems associated with adversarial spectrum learning via analytical modeling, comprehensive simulations, and experimental evaluations. Specifically, the research team aims at (i) formulating the adversarial spectrum learning strategies that can be used by malicious attacks to disrupt the spectrum efficiency and evaluating their damaging impacts in varying wireless and network conditions; (ii) detecting adversarial spectrum learning attacks via new non-parametric detection methods; (iii) creating attack prevention and secure management methods for secure and efficient spectrum access in the potential presence of adversarial spectrum learning, and (iv) comprehensively evaluating the efficiency and effectiveness of the proposed detection and prevention strategies. Appropriate elements from the project will also be integrated into educational materials.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.