Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Omar Almomani has a total of 184 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    TRIDENT-SE: Translation-Divergence and Intent Graph Learning for Cross-Lingual Phishing and Social Engineering Detection in Arabic–English Communication

    by Amjed Ahmed, Inbithaq Ahmed Shakir, Hamood Mohammed Al-Rumhi, Aladdin Al Zahran, Mohammad Ahmed Alomari, Reema Thabit, Omar Almomani, Sumaia Mohammed Al-Ghuribi, Taher M. Ghazal

    In multilingual communication, dialectal differences, code-switching, and culturally influenced persuasive approaches make phishing and social engineering attacks more widespread, testing existing detection technologies. Traditional monolingual and multilingual transformer-based methods concentrate on lexical and semantic similarities and are less resistant to paraphrase or translation-induced semantic changes. TRIDENT-SE (Translation-Divergence and Intent Graph-based Detection of Social Engineering) is a hybrid cross-lingual cyber threat detection system that uses massive language models and graph-based behavioral reasoning. An instruction-tuned Large Language Model contextualizes English, Modern Standard Arabic, regional Arabic dialects, and romanized Arabic phrases. TDE modules assess semantic differences between original and translated messages, enhancing translation noise and language change resilience. An Intent–Action Graph Reasoning (IAGR) module simulates attacker strategies by correlating urgency, impersonation, credential solicitation, authority exploitation, and money demands. TRIDENT-SE increases F1-score by 9.4% over monolingual baselines and 5.1% over state-of-the-art multilingual transformer models in code-switching, dialect-shift, and adversarial paraphrase situations on an annotated Arabic–English dataset. Arabic-speaking human-centered evaluation participants had 18.7% more correct risk assessments and 22.3% less harmful user responses. Multilingual phishing and social engineering detection is robust and interpretable using translation-aware semantic analysis and intent-driven graph learning.

  • Open Access

    A Q-learning-based mobility-aware tree routing protocol in wireless body area networks

    by Mehdi Hosseinzadeh, Jawad Tanveer, Amir Masoud Rahmani, Parisa Khoshvaght, Mohammad Sadegh Yousefpoor, Efat Yousefpoor, Omar Almomani, Thantrira Porntaveetus, Sadia Din

    Wireless body area networks (WBANs) are widely used in both medical and non-medical applications. In these networks, routing protocols face specific challenges due to energy constraints, bandwidth limitations, heterogeneity, node mobility, and dynamic topology. Although reinforcement learning (RL), particularly Q-learning, can improve routing performance in WBANs, existing Q-learning-based approaches often suffer from large state spaces, slow convergence, fixed learning parameters, inefficient topology management, and limited capability to recover routing failures. This study proposes a Q-learning-based mobility-aware tree routing protocol (QMTR) for WBANs integrated with vehicular ad hoc networks (VANETs) to support reliable transmission of passengers’ health data to remote medical centers. QMTR employs a two-stage screening mechanism to reduce the learning space. The first screening stage retains only neighboring nodes that provide geographical progress toward the destination, whereas the second stage eliminates routing candidates that may violate the tree structure. Furthermore, the learning rate is dynamically adjusted according to a comprehensive link-quality index consisting of link lifetime, link delay, and link stability. The protocol further incorporates an adaptive hello-message interval to balance topology accuracy and routing overhead, and a recovery mechanism that temporarily relaxes routing constraints to reconnect isolated nodes without restarting the learning process. Extensive simulations are conducted using Network Simulator 3 (NS3) to evaluate QMTR against existing routing schemes, including ARMR, VehiHealth, and GPSR, under varying vehicle speeds and packet-sending rates. In the first simulation scenario, the evaluation outcomes show that QMTR improves packet delivery rate (PDR) and network lifespan by 3.58% and 8.38%, respectively, and reduces end-to-end delay (EED) by 28.15%. Although QMTR introduces approximately 9.57% higher routing overhead than ARMR in this scenario, it achieves better reliability and energy efficiency. In the second simulation scenario, QMTR increases PDR and network lifespan by 3.73% and 6.48%, respectively, and decreases EED and RO by 21.92% and 13.70%, respectively.

  • Open Access

    Performance Evaluation of FTTH WDM-PON Networks for Fog Computing Infrastructure in Urban Environments

    by Sarra Benadla, Mohammed Debbal, Omar Almomani

    The expansion of IoT and latency-sensitive applications has driven the adoption of Fog Computing, which pushes computational resources to the network edge. The performance of such infrastructures depends critically on the underlying optical access network. This study evaluates FTTH WDM-PON networks for interconnecting Fog nodes in urban environments by comparing star and tree topologies through OptiSystem simulations. Performance was assessed via Q-factor, BER, and eye diagrams under varying power (-7 to +5 dBm), distance (5 to 150 km), and bit rate (2.5 to 100 Gbit/s). The star topology consistently outperforms the tree topology, achieving Q-factor > 10 and BER < 10⁻²⁷ up to 50 km and 10 Gbit/s, while the tree topology degrades rapidly beyond 25 km. These results demonstrate that the star topology is the preferred choice for critical Fog applications requiring high bandwidth and reliability. We provide practical recommendations for network operators regarding topology selection and node positioning for FTTH-based Fog Computing deployments in urban areas.

  • Open Access

    Toward Equitable Arabic Cybersecurity Literacy: A Rubric-Constrained LLM Framework for Phishing Detection and Bilingual Translation Fidelity

    by Taher M. Ghazal, Fareeha Anwar, Sumaia Mohammed Al-Ghuribi, Amjed A. Ahmed, Ali Hamzah Najim, Omar Almomani, Prabu Pachiyannan, Hesham A. Sakr

    Arabic-speaking populations face disproportionate cybersecurity risks due to the predominantly English-centric design of existing awareness materials, which fail to accommodate Arabic dialectal diversity, script complexity, and culturally embedded communication patterns. These deficiencies impair users’ ability to interpret phishing messages, authentication requests, and security alerts, increasing susceptibility to social engineering, identity theft, and data breaches. This paper presents SECURE-A2RC, a rubric-constrained, Arabic-aware large language model framework designed to deliver scalable, interpretable, and culturally relevant cybersecurity education. The framework comprises two coupled components. The first, the Arabic-Aware Secure Communication Encoder (A-SCE), employs an instruction-tuned LLM to produce multidimensional encodings that capture three learner competencies: security intent comprehension; linguistic deception cue recognition encompassing urgency, authority impersonation, and incentive framing; and action-critical translation fidelity across Arabic dialectal registers and Arabic–English bilingual contexts. The second, the Rubric-Constrained Adaptive Feedback Generator (RCAFG), translates A-SCE encodings into personalized, expert-aligned instructional feedback and proficiency-calibrated adaptive tasks, ensuring pedagogical consistency, security correctness, and dialect awareness throughout the learning cycle. The framework is evaluated on three domain-relevant corpora: the English–Arabic Parallel Phishing Email Corpus, the Open MalSec dataset, and the Arabic Spam and Ham Tweets dataset. SECURE-A2RC achieves a 31% improvement in phishing identification accuracy and a 26% reduction in action-critical translation errors compared to conventional awareness materials. A comparative evaluation against SERENA, a Multi-Agent LLM, and the Arabic Multitask Learning Model confirms consistent superiority across detection accuracy, F1-score, dialectal robustness, and educational effectiveness metrics, affirming rubric-constrained LLM integration as a viable approach to equitable multilingual cybersecurity education.

  • SA-LDP-DW: a dual-protection framework for trustworthy privacy-preserving data publishing

    by Omar Almomani, K. L. Raghavender Reddy, Vikram V. Patel, Sumit Sharma, B. Jayaprakash, Prabhat Kumar Sahu, Monika Singla, A. Siva Sangari, Devendra Singh

  • Open Access

    Optimizing Resource Allocation and Enhancing Security in Cloud Systems: A Data-Centric Approach

    by Mohammed Al Masarweh, Tariq Alwada’N, Adel Mohammad Hamdan, Omar Almomani, Isra’A Mustafa

    High-performance resource orchestration and robust data security represent critical, often competing, operational objectives in modern cloud computing architectures. This study presents a unified infrastructure framework designed to reconcile these requirements by integrating a Geographically Aware Placement Algorithm (GAPA) with an Artificial Intelligence-Driven Monitoring system (AIDAM). GAPA dynamically optimizes workload distribution based on regional server capacity and geographic proximity, while AIDAM leverages deep unsupervised autoencoders for real-time anomaly detection and threat mitigation. The framework was evaluated via deterministic simulation using production traces from the Google Cluster Data (2019) corpus under a systematic injection of volumetric Distributed Denial-of-Service (DDoS) anomalies. The empirical results demonstrate a 92% macro-averaged threat detection accuracy rate against low-and-slow traffic variations alongside a minimal cryptographic processing latency overhead of 3–5% relative to an unencrypted baseline scheduling configuration. Furthermore, the integrated pipeline achieved a 25% reduction in end-to-end network latency compared to traditional non-geographically aware heuristic models. These findings demonstrate that cloud infrastructure efficiency and security resilience can be simultaneously enhanced without requiring comprehensive physical re-engineering.

  • Open Access

    Predicting Chronic Kidney Disease from Biomarkers: An Explainable Machine Learning Approach

    by Abass Al-Momany, Omar Almomani, Ensaf Y. Almomani

    Background/Objectives: Chronic kidney disease (CKD) remains underdiagnosed until advanced stages, motivating reliable, clinically deployable screening models that pair high discrimination with an explicit operating threshold and transparent explanations. Methods: In this study, we propose a CKD detection framework that integrates structured preprocessing, class imbalance handling, stratified 10-fold cross-validation with out-of-fold (OOF) prediction, and clinically oriented threshold selection via the Youden index, followed by explainability using SHAP and LIME. Experiments were conducted on two datasets. Across a broad panel of ten machine learning models, gradient boosting methods consistently dominated. Results: LightGBM achieved the best overall clinical composite performance on both datasets. On Dataset 1, LightGBM delivered near-ceiling OOF discrimination (ROC-AUC = 99.98, PR-AUC = 99.98) and an excellent clinically balanced performance at the best Youden threshold (0.41), reaching sensitivity = 99.20, specificity = 99.60, accuracy = 99.40, F1 = 99.40, and MCC = 98.80, with robust cross-validation stability (CV AUC = 99.99 ± 0.04; CV sensitivity = 99.10 ± 1.81; CV specificity = 99.46 ± 1.42; CV MCC = 98.59 ± 2.19), strong calibration (Brier = 0.006), and fast training (0.078 ± 0.019 s/fold). On Dataset 2, LightGBM maintained high generalization (ROC-AUC = 99.72, PR-AUC = 99.64) and clinically deployable balance at the best Youden threshold (0.35), achieving sensitivity = 98.10, specificity = 98.03, accuracy = 98.06, F1 = 98.06, and MCC = 96.13, with consistent fold-wise performance (CV AUC = 99.69 ± 0.25; CV sensitivity = 97.25 ± 1.25; CV specificity = 98.11 ± 1.02; CV MCC = 95.37 ± 1.56), acceptable calibration (Brier = 0.0173), and practical training time (0.742 ± 0.144 s/fold). Conclusions: Finally, SHAP and LIME explanations confirmed that model decisions align with clinically meaningful renal function and symptom/biomarker patterns at both population and patient levels, supporting safer translation of the proposed framework into CKD screening and decision-support workflows.


  • SEWFIR: A Secure Self-Embedding Watermarking Framework for Image Recovery in IoT-Driven Networks

    by Omar Almomani, M. Ambika, Yagna B. Adhyaru, Gadug Sudhamsu, Manoranjan Parhi, P. Ajitha, Sudeep Varshney, Vikas Wasson, Rajesh Singh

  • Open Access

    A metaheuristic feature selection model using bat optimization for malicious URL attack detection

    by Omar Almomani, Mahran Al-Zyoud, Yazeed Alsarhan, Ammar Almomani, Thair Khdour, Khaled Mohammad Alomari, Said A. Salloum

    The malicious URLs have been a constant threat to cybersecurity because hackers are constantly creating phishing, malware, spam, and defacement links that resemble authentic Web layouts and bypass static security measures. Despite very promising results of machine learning (ML) and deep learning (DL) models in URL classification, the effectiveness of these models is usually limited by high dimensional spaces of features that have redundant and irrelevant qualities, which leads to increased computation costs and potentially less generalization ability. To cope with this, this study will present a wrapper-based Bat Algorithm (BA) feature selection model to determine small and discriminative subsets of features in detecting malicious URLs. The bio-inspired metaheuristic BA offers a good tradeoff of exploration and exploitation in high dimensional optimization issues and thus is useful in feature subset selection. The proposed BA model is tested on ensemble ML (XGBoost, AdaBoost, Gradient Boosting, CatBoost and LightGBM) and DL (CNN, RNN, LSTM and CNN-LSTM) architectures with two datasets the multi-class ISCX-URL-2016 dataset and the more recent URL Phishing (2026) dataset. Experiments results indicate that BA has a significant dimensionality reduction: It reduces original feature space on ISCX-URL-2016 by 51.90% in the case of Defacement, by 67.09% in the case of Malware, by 49.37% in the case of Phishing, by 59.49% in the case of Spam, and 45.91% in the case of Phishing on URL Phishing (2026). This reduction notwithstanding, BA shows consistent improvements in the classification of both datasets. BA-enhanced LightGBM had the best overall results of all the tested models, with an accuracy of 99.92% on ISCX-URL-2016 and 98.17% on URL Phishing (2026), and high values of ROC-AUC and good computational efficiency. A statistical analysis also supports the fact that the improvements noticed are significant. Altogether, the proposed BA-based feature selection model is an efficient, scalable, and reliable solution to malicious URL detection intelligent, with good possibilities of being implemented into real-world systems in terms of cybersecurity.


  • Reinforcement Learning for Autonomous Threat Mitigation in AI-Driven Metaverse Environments

    by Mohammad Alauthman, Ala Hamarsheh, Amjad Aldweesh, Ahmad Al-Qerem, Thair Al Fararjeh, Omar Almomani

    Metaverse environments now blend embodied interaction, synthetic media, virtual asset trading, and platform governance in persistent multi-user worlds. But conventional cybersecurity? It's necessary yet insufficient--treating threats as isolated technical incidents ignores their social impact. This chapter proposes an ontology-guided reinforcement learning framework for autonomous threat mitigation. It models actors, assets, interactions, threats, governance constraints, and control options as a linked semantic system that shapes state construction, action boundaries, reward design, explainability, and cross-platform learning. We identify eight knowledge mechanisms that boost context awareness, ensure proportional responses, and enable auditability. Privacy, fairness, scalability, accountability, and adversarial adaptation remain key challenges. Ultimately, trustworthy metaverse defense demands semantically grounded, governance-aware adaptive agents.