Fatmah Omer Bamashmoos

@kau.edu.sa

Faculty of Computing and Information Technology
King Abdulaziz University

Fatmah Omer Bamashmoos


               Download Compact PDF  
https://researchid.co/fatmahb

RESEARCH INTERESTS

Artificial Intelligence, Knowledge Base, Semantic Modelling, Internet of Things, Cybersecurity
5

Scopus Publications

18

Scholar Citations

2

Scholar h-index

Scopus Publications

  • Trustworthy Federated Learning with Blockchain-Based Consensus for Mitigating Poisoning Attacks in Healthcare Systems
    Raghad Hamed Alhamrani, Fatmah Omar Bamashmoos, Enas Fawzi Khairallah
    Information Switzerland, 2026
    This paper presents a framework that integrates blockchain-enabled Federated Learning (FL) with consensus mechanisms to mitigate poisoning attacks in healthcare environments. The framework incorporates blockchain consensus mechanisms, with Proof-of-Work (PoW) used as a baseline and Proof-of-Stake (PoS) adopted as the proposed approach; both are evaluated independently within the same Secure Multiparty Computation (SMPC)-enabled federated learning architecture for privacy preservation. The proposed system is evaluated on the OCTMNIST and TissueMNIST datasets under both centralized and federated settings, including poisoning scenarios with 10% and 50% malicious clients. Results show that consensus-aware aggregation reduces the influence of unreliable client updates and improves the robustness of the global model under poisoning conditions. In addition, the framework prioritizes trustworthy client contributions during aggregation, supporting reliable model sharing in collaborative healthcare learning environments. Unlike prior blockchain-based federated learning defenses that introduce heavy cryptographic overhead, the proposed PoS-based aggregation explicitly balances robustness and computational efficiency, enabling practical deployment under high poisoning ratios.
  • Adaptive Privacy-Preserving Insider Threat Detection Using Generative Sequence Models
    Fatmah Bamashmoos
    Future Internet, 2026
    Insider threats remain one of the most challenging security risks in modern enterprises due to their subtle behavioral patterns and the difficulty of distinguishing malicious intent from legitimate activity. This paper presents a unified and adaptive generative framework for insider threat detection that integrates Variational Autoencoders (VAEs) and Transformer Autoencoder architectures to learn personalized behavioral baselines from sequential user event logs. Anomalies are identified as significant deviations from these learned baseline distributions. The proposed framework incorporates an adaptive learning mechanism to address both cold-start scenarios and concept drift, enabling continuous model refinement as user behavior evolves. In addition, we introduce a privacy-preserving latent-space design and evaluate the framework under formal privacy attacks, including membership inference and reconstruction attacks, demonstrating strong resilience against data leakage. Experiments performed on the CERT Insider Threat Dataset (v5.2) show that our approach outperforms traditional and deep learning baselines, with the Transformer Autoencoder achieving an F1-score of 0.66 and an AUPRC of 0.59. The results highlight the effectiveness of generative sequence models for privacy-conscious and adaptive insider threat detection in enterprise environments, providing a comparative analysis of two powerful architectures for practical implementation.
  • Towards Asthma Self-Management: An Integrated Ontology Model for Asthma Action Plan
    Fatmah Bamashmoos, Theo Tryfonas
    Proceedings 2019 IEEE International Conference on Bioinformatics and Biomedicine Bibm 2019, 2019
    Asthma is a chronic disease that cannot be cured but however it can be managed. There are different ways for Asthma management and the Asthma Action Plan is one of the self-management methods used for managing and monitoring a patient's condition. In this paper, we use an ontology-based method to identify and classify Asthma Action Plan terminologies and integrate respective models with demographics of asthma patients for the purpose of personalisation. We propose a personalised Asthma Patients Profile Model and integrate it with an Action Plan Model and Asthma Disease Model. These can be subsequently used for the development of software applications integrating patient records and contextual data from wearables and sensors, in order to provide personalised disease management plans per patient.
  • A review of air quality sensing technologies and their potential interfaces with IoT for asthma management
    Fatmah Bamashmoos, Pete Woznowski, Theo Tryfonas
    ACM International Conference Proceeding Series, 2018
    In recent years significant advancement has been achieved on the domain of assessing air quality and monitoring the condition of asthma based on sensing technology. The pervasiveness of relevant devices could have a powerful impact on enabling patients self-monitoring and increasing public awareness on the air they breathe. In this study, we investigated a variety of different sensors devices relevant to the monitoring of air quality and different devices for assessing the condition of asthma. Our approach at this stage has been based on feature comparison based on product specification sheets and published case studies. We found that there is no standardisation among such devices and that in order for someone to deliver a holistic intervention for the management of a condition like asthma, a significant amount of proprietary effort to integrate third party data and technologies would be required. Such a solution would include both typical air quality sensing and asthma indicators monitoring, but also elements to seamlessly integrate sensed data and logic about the management of the condition.
  • Towards Secure SPARQL Queries in Semantic Web Applications Using PHP
    Fatmah Bamashmoos, Ian Holyer, Theodore Tryfonas, Przemyslaw Woznowski
    Proceedings IEEE 11th International Conference on Semantic Computing ICSC 2017, 2017
    The Semantic Web (SW) is a significant advancement in the field of Internet technologies and an uncharted territory as far as security is concerned. In this paper, we investigate and assess the impact of known attacks of SPARQL/SPARUL injections on Semantic Web applications developed in PHP. We highlight future challenges of developing robust Semantic Web applications using PHP. Our results demonstrate and quantify impacts on Confidentiality, Integrity and Availability (CIA) breaches of data in Semantic Web applications. Our recommendations are targeted to PHP developers, to encourage them to integrate security as early in their design and coding practice as possible.

RECENT SCHOLAR PUBLICATIONS

  • An Action Plan Knowledge Base to Support Asthmatic Patients with a Potential Interface Using IoT Devices
    FOS Bamashmoos
    University of Bristol , 2022
    2022
  • Towards asthma self-management: An integrated ontology model for asthma action plan
    F Bamashmoos, T Tryfonas
    2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM … , 2019
    2019
    Citations: 1
  • A review of air quality sensing technologies and their potential interfaces with IoT for asthma management
    F Bamashmoos, P Woznowski, T Tryfonas
    Proceedings of the 11th PErvasive Technologies Related to Assistive … , 2018
    2018
    Citations: 9
  • Towards secure SPARQL queries in semantic web applications using PHP
    F Bamashmoos, I Holyer, T Tryfonas, P Woznowski
    2017 ieee 11th international conference on semantic computing (icsc), 276-277 , 2017
    2017
    Citations: 8
  • Towards Secure SPARQL Queries in Semantic Web Applications using PHP (Extended Version)
    F Bamashmoos, I Holyer, T Tryfonas, P Woznowski
    arXiv preprint arXiv:1701.07671 , 2017
    2017

MOST CITED SCHOLAR PUBLICATIONS

  • A review of air quality sensing technologies and their potential interfaces with IoT for asthma management
    F Bamashmoos, P Woznowski, T Tryfonas
    Proceedings of the 11th PErvasive Technologies Related to Assistive … , 2018
    2018
    Citations: 9
  • Towards secure SPARQL queries in semantic web applications using PHP
    F Bamashmoos, I Holyer, T Tryfonas, P Woznowski
    2017 ieee 11th international conference on semantic computing (icsc), 276-277 , 2017
    2017
    Citations: 8
  • Towards asthma self-management: An integrated ontology model for asthma action plan
    F Bamashmoos, T Tryfonas
    2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM … , 2019
    2019
    Citations: 1
  • An Action Plan Knowledge Base to Support Asthmatic Patients with a Potential Interface Using IoT Devices
    FOS Bamashmoos
    University of Bristol , 2022
    2022
  • Towards Secure SPARQL Queries in Semantic Web Applications using PHP (Extended Version)
    F Bamashmoos, I Holyer, T Tryfonas, P Woznowski
    arXiv preprint arXiv:1701.07671 , 2017
    2017