Hamza RAFIK

Mr. Hamza RAFIK

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 February 2023 in International Journal of Online and Biomedical Engineering (iJOE)
Verified
Journal Article
Open access
PDF file
HRHamza RAFIK
Hamza RAFIK
AMAbderrahim Maizate
Abderrahim Maizate
AEAbdelaziz Ettaoufik
Abdelaziz Ettaoufik
In the new era, the trend of using wearable devices and smart accessories gained considerable popularity and become a necessity utility for human life due to their major role to keep monitoring health conditions and providing healthcare services. The combination of IoT networks with edge computing paradigms develops an intelligent e-health system that aims to monitor different real-time scenarios. The deployment of an e-health system exposes several challenges regarding the security and privacy aspects, particularly in the case of dealing with an enormous quantity of medical data and the risk presented by exchanging operations with external entities. In this paper a comprehensive presentation covered the basic topics of e-health system layers thus the advantages and limitations in terms of existing challenges has been mentioned, subsequently, adapted to the exposed cyber risk through the traditional systems in exchanging medical data, a discussion of the blockchain technology come over for new application opportunities, where this approach efficiently ensure the security of data transactions over the network, in addition, an overview outlined the main research works related to this technology. Therefore, a presentation study of diverse works reveals different security framework solutions related to e-health system’s layers, furthermore, uncovering the benefits of integrating intelligent technologies such as Machine Learning (supervised, and unsupervised types), Deep Learning, and Reinforcement Learning as well as introducing a comparison analysis of multiple AI algorithm models based on their efficiency for future deployment related security purposes to provide a smart healthcare monitoring system that meets patient needs. The end of this review highlighted further research directions and the actual open challenges regarding the e-Health system’s limitations.

8 October 2025
Verified
Book Chapter
Closed access
PDF file
HRHamza RAFIK
Hamza RAFIK
AEAbdelaziz Ettaoufik
Abdelaziz Ettaoufik
AMAbderrahim Maizate
Abderrahim Maizate

12 November 2026 in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
Verified
Journal Article
Closed access
HRHamza RAFIK
Hamza RAFIK
AEAbdelaziz Ettaoufik
Abdelaziz Ettaoufik
AMAbderrahim Maizate
Abderrahim Maizate
The rise of Internet of Medical Things (IoMT) and edge computing in healthcare demands intrusion detection systems (IDS) that protect sensitive patient data without sacrificing detection quality. Federated learning (FL) enables collaborative training of such detectors without sharing raw data; however, existing FL-based IDS remain vulnerable to model inversion and poisoning attacks during client–server communication, and the compared state-of-the-art solutions implement no formal privacy mechanism. This paper presents FlowerFED-IDS, a federated IDS built on the Flower framework that unifies three mechanisms in a single stack: a hybrid 1D CNN–BiLSTM detection model, local differential privacy (LDP) that clips and perturbs model updates before transmission, and robust FedTrimmedAvg aggregation. On the CICIoMT2024 dataset, under IID partitioning as a controlled baseline, FlowerFED-IDS achieves accuracies of 96.38%, 93.03%, and 93.89% with 5, 10, and 15 clients, respectively, maintaining recall above 93% in all configurations. Under a poisoning scenario with 20% compromised clients, FedTrimmedAvg keeps accuracy within 0.5 percentage points of the honest baseline. A privacy–utility analysis over noise multipliers identifies σ = 0.10 as the operating point satisfying the 95% clinical recall floor; we report its composed budget transparently (ε = 1215 at δ = 10 −5 over 20 rounds), a quantified but loose bound providing practical protection against update-reconstruction and inference attacks rather than a strict differential-privacy guarantee. A preliminary non-IID evaluation with Dirichlet α = 0.5, further confirms that the framework remains operational under realistic data heterogeneity, with recall above the clinical threshold, at the cost of reduced early-training stability.

8 May 2023 in ITM Web of Conferences
Verified
Journal Article
Open access
PDF file
HRHamza RAFIK
Hamza RAFIK
AEAbdelaziz Ettaoufik
Abdelaziz Ettaoufik
AMAbderrahim Maizate
Abderrahim Maizate
Current health situations and crises require physicians and researchers to convert traditional healthcare services to a new generation of digital healthcare known as e-health smart systems that operate close to the end user with the objective to provide medical assistance using advanced technologies including Internet of Medical Things technology, edge computing, and cloud computing paradigms. However, this system architecture reveals limitations in terms of latency, bandwidth, power consumption as well as security and privacy of collected data. Through this paper, a presentation of different healthcare monitoring system layers has been defined, in addition to listed challenges faced by the deployment of this technology, while providing an introduction of security risks that threaten the user data safety alongside the e-health layers. Moreover, a summarized discussion of Blockchain technology came over to provide a secure decentralized architecture in sharing data across allowed entities.