FindAPhD Weekly PhD Newsletter | JOIN NOW FindAPhD Weekly PhD Newsletter | JOIN NOW

Deep Learning-enhanced Device Authentication for Internet of Things

   Department of Electrical Engineering and Electronics

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

Click here to search for PhD studentship opportunities
  Dr J Zhang, Prof Yao-Win Peter Hong  No more applications being accepted  Funded PhD Project (Students Worldwide)

About the Project

This project is part of a 4 year Dual PhD degree programme between the National Tsing Hua University (NTHU) in Taiwan and the University of Liverpool in England. As Part of the NTHU-UoL Dual PhD Award students are in the unique position of being able to gain 2 PhD awards at the end of their degree from two internationally recognised world leading Universities. As well as benefiting from a rich cultural experience, Students can draw on large scale national facilities of both countries and create a worldwide network of contacts across 2 continents.

Internet of things (IoT) has digitally transformed our everyday life which aims to connect everything and everyone. There will be massive IoT devices connected wirelessly with each other; Cisco predicts there will be 300 billion IoT devices by 2030. However, the broadcast nature of wireless transmissions makes device authentication challenging as any malicious users can access the network. The conventional cryptography-based solutions rely on a pre-shared key and software address. However, key management and distribution become challenging for IoT devices, as many of them will be low-cost and distributed in remote areas. Software address, such as MAC/IP address, is not encrypted and can be spoofed easily.

This PhD project proposes an emerging technique named radio frequency fingerprint identification (RFFI), which exploits unique hardware features of transmitters as their identifiers. These features are produced because of the manufacturing process variations, which cannot be eliminated even with advanced manufacturing technologies. The hardware features deviate from the nominal values and will slightly affect the waveform of wireless transmissions, but the deviation is within such a small range that it does not affect the normal communication operation. As these impairments are unique, stable and difficult to tamper with, they can be extracted as device identifiers. RFFI is a multi-class classification problem and the state-of-the-art deep learning can be leveraged. 

This project will employ deep learning to design a robust, smart and secure RFFI system. A synergistic approach involving theoretical modelling and experimental validation will be adopted. WiFi will be used as a case study. Comprehensive experimental validation will be carried out, which will create practical and viable RFFI protocols.

Academic Requirements

Applicants for postgraduate research study at Liverpool are normally expected to hold a UK first degree with a First Class or Upper Second Class degree classification, or a Second Class degree plus a Master’s degree.

The following skills will be highly desirable:

·        Background in wireless communication, wireless security, or computer science

·        Good programming skills

·        Experience of using software defined radios

English Language Requirements 

Students from the UK will normally be expected to have a GCSE in English at grade 4 or above, or an equivalent qualification.

For students whose first language is not English, the University’s minimum requirements are the IELTS test with a minimum overall score of 6.5, and no less than 5.5 in each of the sub-tests (reading, writing, speaking and listening) or an equivalent qualification. 

For academic enquires please contact Dr. Junqing Zhang, [Email Address Removed] & Prof Yao-Win Peter Hong  [Email Address Removed]

For enquires on the application process or to find out more about the Dual programme please contact [Email Address Removed]

To apply please visit: When applying please ensure you Quote the supervisor & project title you wish to apply for and note ‘NTHU-UoL Dual Scholarship’ when asked for details of how plan to finance your studies.

Funding Notes

It is planned that students will spend the first year at University of Liverpool, Followed by 2 years at NTHU, and then returning to the University of Liverpool for the final year of study.
Both the University of Liverpool and NTHU have agreed to waive the tuition fees for the duration of the project and stipend of TWD 11,000/month will be provided as a contribution to living costs (the equivalent of £280 per month when in Liverpool).


Guanxiong Shen, Junqing Zhang*, Alan Marshall, Linning Peng, and Xianbin Wang, “Radio Frequency Fingerprint Identification for LoRa Using Spectrogram and CNN,” in Proc. IEEE INFOCOM, 2021, accepted.
Linning Peng, Junqing Zhang, Ming Liu and Aiqun Hu, “Deep Learning Based RF Fingerprint Identification Using Differential Constellation Trace Figure,” IEEE Transactions on Vehicular Technology, vol. 69, no. 1, pp. 1091 - 1095, Jan. 2020
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.
PhD saved successfully
View saved PhDs