Adel Samir ElZemity

Office B2.12

Keynes College

University of Kent

Canterbury, Kent, UK CT2 7FS

Previously

Earned a bachelor’s degree in computer engineering from Nile University in Egypt.
Did exchange semesters at Riga Technical University in Latvia and Fayetteville State University in the USA, in computer science.
Worked as Machine Learning Engineer at Spanish National Cancer Research Center (CNIO) in Spain, specializing in Natural Language Processing (NLP).

Currently

Pursuing a Ph.D. in Computer Science at University of Kent, UK.
Conducting research on the security and privacy implications of Large Language Models (LLMs) and artificial intelligence systems, with a focus on mitigating vulnerabilities and enhancing robustness.
Engaged in the development of lightweight machine learning solutions to address ransomware threats in Internet of Things (IoT) environments. This work is part of the “Countering HArms caused by Ransomware on the Internet of Things (CHARIOT)” project, in collaboration with esteemed researchers including Dr. Budi Arief, Dr. George Oikonomou, Dr. James Pope, Dr. Calvin Brierley, and Dr. Yuxiang Huang.

News

Feb 18, 2025	Second PhD Paper Submitted to SIGIR 2025
Dec 11, 2024	Presenting at University of Kent Winter Showcase 2024
Nov 26, 2024	Submitted AISI Systemic AI Safety Grant Application
Oct 08, 2024	Leading CyberFirst Girls Competition Workshop
Sep 01, 2024	Submitted Grant Application to Alan Turing Institute's Defence & Security Program

Selected Publications

CyberLLMInstruct: A New Dataset for Analysing Safety of Fine-Tuned LLMs Using Cyber Security Data

Adel ElZemity, Budi Arief , and Shujun Li

2025

Bib PDF Website

@misc{elzemity2025cyberllminstructnewdatasetanalysing,
  title = {CyberLLMInstruct: A New Dataset for Analysing Safety of Fine-Tuned LLMs Using Cyber Security Data},
  author = {ElZemity, Adel and Arief, Budi and Li, Shujun},
  year = {2025},
  eprint = {2503.09334},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
}

Privacy Threats and Countermeasures in Federated Learning for Internet of Things: A Systematic Review

Adel ElZemity, and Budi Arief

In 2024 IEEE International Conferences on Internet of Things (iThings) and IEEE Green Computing & Communications (GreenCom) and IEEE Cyber, Physical & Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics , 2024

Bib PDF Website

@inproceedings{10731741,
  author = {ElZemity, Adel and Arief, Budi},
  booktitle = {2024 IEEE International Conferences on Internet of Things (iThings) and IEEE Green Computing & Communications (GreenCom) and IEEE Cyber, Physical & Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics},
  title = {Privacy Threats and Countermeasures in Federated Learning for Internet of Things: A Systematic Review},
  year = {2024},
  pages = {331-338},
  keywords = {Privacy;Differential privacy;Social computing;Computational modeling;Multi-party computation;Robustness;Blockchains;Internet of Things;Time factors;Security;Federated Learning;Internet of Things;Privacy Threats;Defensive Measures;Systematic Literature Review},
  doi = {10.1109/iThings-GreenCom-CPSCom-SmartData-Cybermatics62450.2024.00072}
}

A Comparative Analysis of Time Series Transformers and Alternative Deep Learning Models for SSVEP Classification

Heba Ali , Adel ElZemity, Amir E Oghostinos , and 1 more author

In International Conference on Model and Data Engineering , 2023

Abs Bib Website

Steady State Visually Evoked Potentials (SSVEPs) are intrinsic responses to specific visual stimulus frequencies. When the retina is activated by a frequency ranging from 3.5 to 75 Hz, the brain produces electrical activity at the same frequency as the visual signal, or its multiples. Identifying the preferred frequencies of neurocortical dynamic processes is a benefit of SSVEPs. However, the time consumed during calibration sessions limits the number of training trials and gives rise to visual fatigue since there is significant human variation across and within individuals over time, which weakens the effectiveness of the individual training data. To address this issue, we propose a novel cross-subject-based classification method to enhance the robustness of SSVEP classification by employing cross-subject similarity and variability. Through an efficient time-series transformer, we compared Time Series Transformers (TST) with different deep learning approaches in the literature. We utilized the TST to speed up calibration processes and improve classification precision for new users. Then we compare this technique to other techniques: EEGNet, FBtCNN, and C-CNN. Our suggested framework’s outcomes are validated using two datasets with two different time window lengths. The experimental results suggest that cross-subject time-series transformers and EEGNet achieve better performance with specific subjects than state-of-the-art techniques when compared to other techniques that have high potential for building high-speed BCIs.
@inproceedings{ali2023comparative, title = {A Comparative Analysis of Time Series Transformers and Alternative Deep Learning Models for SSVEP Classification}, author = {Ali, Heba and ElZemity, Adel and Oghostinos, Amir E and Selim, Sahar}, booktitle = {International Conference on Model and Data Engineering}, pages = {3--16}, year = {2023}, organization = {Springer}, isbn = {978-3-031-55729-3}, publisher = {Springer Nature Switzerland}, doi = {10.1007/978-3-031-55729-3_2} }