CAREER: Data-Driven Wireless Networking Designs for Efficiency and Security

职业：数据驱动的无线网络设计以提高效率和安全性

• 批准号: 2044516
• 负责人: Zhuo Lu
• 金额: $ 50万
• 依托单位: University of South Florida
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2026-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2044516&HistoricalAwards=false
• 关键词: CAREER; Data; Driven; Wireless; Networking

Today's wireless networks are being re-shaped by ubiquitous wireless connectivity and emerging network architectures. To meet the increasingly growing demand from the users for more efficient, reliable, and secure wireless network services, the project aims at exploring the new dimension of creating data-driven approaches towards improving the wireless network performance and security. One key difference between the proposed data-driven approaches and traditional network designs is that the online data due to network behaviors and activities will be collected, processed, and used in systematic ways towards improving wireless network efficiency, reliability, and security. The research will create, design, and optimize efficient methodologies to categorize, process, classify, use, and validate wireless network data for network performance and security.The project will focus on efficiently harnessing and leveraging the online data observed in wireless networking to improve network efficiency and security. Specifically, the research team in this project aims at i) creating data-driven approaches based on network link data to improve the throughput performance of the wireless links, ii) effectively managing and mitigating wireless collisions and interference by collecting and processing network control and data packets, iii) understanding how new security threats and attack strategies can emerge and behave based on observed network data in the wireless channel as well as designing effective countermeasure against such threats and attacks, iv) conducting extensive simulations and experimental evaluations to validate the data-driven approaches towards wireless network efficiency, reliability and security. In addition, appropriate elements in the research from the project will be integrated into educational materials. The research results will also be widely disseminated to the public.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.

如今，无处不在的无线连接和新兴的网络架构正在重塑无线网络。为了满足用户对更高效、可靠和安全的无线网络服务日益增长的需求，该项目旨在探索创建数据驱动方法的新维度，以提高无线网络的性能和安全性。所提出的数据驱动方法与传统网络设计的一个关键区别在于，由于网络行为和活动而产生的在线数据将被系统地收集、处理和使用，以提高无线网络的效率、可靠性和安全性。该研究将创建、设计和优化有效的方法，对无线网络数据进行分类、处理、分类、使用和验证，以提高网络性能和安全性。该项目将侧重于有效利用和利用无线网络中观察到的在线数据，以提高网络效率和安全性。具体而言，本项目研究团队的目标是i)创建基于网络链路数据的数据驱动方法，以提高无线链路的吞吐量性能；ii)通过收集和处理网络控制和数据包，有效地管理和减轻无线冲突和干扰；Iii)了解新的安全威胁和攻击策略如何基于无线信道中观察到的网络数据出现和行为，以及设计针对此类威胁和攻击的有效对策；iv)进行广泛的模拟和实验评估，以验证数据驱动的无线网络效率、可靠性和安全性方法。此外，该项目的适当研究内容将被纳入教材。研究结果也将向公众广泛传播。该奖项反映了美国国家科学基金会的法定使命，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

MUSTER: Subverting User Selection in MU-MIMO Networks

• DOI: 10.1109/infocom48880.2022.9796815
• 发表时间: 2022-05
• 期刊: IEEE INFOCOM 2022 - IEEE Conference on Computer Communications
• 作者: Tao Hou;Shen Bi;Tao Wang;Zhuo Lu;Yao-Hong Liu;S. Misra;Y. Sagduyu

How Can the Adversary Effectively Identify Cellular IoT Devices Using LSTM Networks?

攻击者如何使用 LSTM 网络有效识别蜂窝物联网设备？

• 发表时间: 2023
• 期刊: ACM Workshop on Wireless Security and Machine Learning
• 作者: Luo, Zhengping;Pitera, Will;Zhao, Shangqing;Lu, Zhuo;Sagduyu, Yalin
• 通讯作者: Sagduyu, Yalin

Data-Driven Next-Generation Wireless Networking: Embracing AI for Performance and Security

• DOI: 10.1109/icccn58024.2023.10230189
• 发表时间: 2023-06
• 期刊: 2023 32nd International Conference on Computer Communications and Networks (ICCCN)
• 作者: Jiahao Xue;Zhe Qu;Shangqing Zhao;Yao-Hong Liu;Zhuo Lu

Undermining Deep Learning Based Channel Estimation via Adversarial Wireless Signal Fabrication

• DOI: 10.1145/3522783.3529525
• 发表时间: 2022-05
• 期刊: Proceedings of the 2022 ACM Workshop on Wireless Security and Machine Learning
• 作者: Tao Hou;Tao Wang;Zhuo Lu;Yao-Hong Liu;Y. Sagduyu