Coventry University Featured PhD Programmes
Engineering and Physical Sciences Research Council Featured PhD Programmes
University of Sheffield Featured PhD Programmes
FindA University Ltd Featured PhD Programmes
FindA University Ltd Featured PhD Programmes

Artificial Intelligence Enhanced Wireless Device Classification Using Radio Frequency Fingerprinting

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  • Full or part time
    Dr J Zhang
    Prof A Marshall
  • Application Deadline
    No more applications being accepted
  • Funded PhD Project (Students Worldwide)
    Funded PhD Project (Students Worldwide)

Project Description

Internet of things (IoT) has been transforming our everyday life via many exciting applications such as smart home, connected healthcare, smart cities, to name but a few. Billions of devices are wirelessly connected, e.g., sensor nodes, fitbit, web cameras, etc. The majority of IoT devices are low cost with very limited computational resources and power supply. This has rendered an overlook on the security provision on IoT devices and unfortunately has resulted in numerous notorious IoT attacks, which have caused significant economic loss and compromised the IoT trustworthiness. The IoT security thus becomes the main bottleneck to promote secured and matured IoT applications.

The user identity authentication is essential to prevent malicious attackers from accessing the network. Conventional authentication is based on the device ID, such as MAC/IP addresses, which however can be tampered and spoofed easily. There is an emerging technique to employ the radio frequency fingerprinting (RFF) to authenticate IoT devices. Similar to the biometric fingerprints of human, radio devices also have their fingerprinting, which represents unique features of wireless transceivers resulted from manufacturing process. These features include oscillator frequency offset, I and Q mismatch, power amplifier non-linearity.

RFF can be exploited to authenticate the identities of wireless devices in a secure and lightweight manner. An authenticator first collects the RFF of the devices and stores them in a database. When the device wants to join the network again, the authenticator will extract the RFF of the candidate device, and compare it with the database to identify the device. This technique has attracted extensive research interests to classify wireless devices, such as WiFi, ZigBee, and LoRa.

There are still many fundamental research challenges to design a robust and reliable RFF identification system. This PhD project thus aims to obtain a better understanding on the RFF and enhance the classification performance using sophisticated artificial intelligence.

To apply for this opportunity, please visit: https://www.liverpool.ac.uk/study/postgraduate-research/how-to-apply/

Funding Notes

The total amount of the studentship will be £20,000 per annum for 3 years. The studentship is available to Home and EU students where a full stipend and full Home/EU Fees will be paid. The studentship is also available to International students but the funding will only cover part of the international tuition fee and no stipend will be available.

References

Wenhao Wang, Zhi Sun, Sixu Piao, Bocheng Zhu, and Kui Ren. "Wireless physical-layer identification: Modeling and validation." IEEE Transactions on Information Forensics and Security 11, no. 9, pp. 2091-2106, 2016.
Tien Dang Vo-Huu, Triet Dang Vo-Huu, and Guevara Noubir. "Fingerprinting Wi-Fi devices using software defined radios." in Proc. 9th ACM Conference on Security & Privacy in Wireless and Mobile Networks, pp. 3-14, 2016.
Pieter Robyns, Eduard Marin, Wim Lamotte, Peter Quax, Dave Singelée, and Bart Preneel. "Physical-layer fingerprinting of LoRa devices using supervised and zero-shot learning." In Proc. 10th ACM Conference on Security and Privacy in Wireless and Mobile Networks, pp. 58-63, 2017.
Linning Peng, Aiqun Hu, Junqing Zhang, Yu Jiang, Jiabao Yu, and Yan Yan, “Design of a hybrid RF fingerprint extraction and device classification scheme,” IEEE Internet of Things Journal, vol. 6, no. 1, pp. 349 – 360, 2019.



FindAPhD. Copyright 2005-2019
All rights reserved.