Education
Ph.D. in Electrical & Computer Engineering, Concordia University, Canada
M.Eng. in Electrical & Computer Engineering, Concordia University, Canada
B.Sc. in Computer Engineering, Jordan University of Science and Technology, Jordan
Certificate in Cybersecurity, Polytechnique Montréal, Technological University, Canada
Research Interests
- Cloud Computing
- Cyber security
- Information Security
- machine learning
- IoT
- 6G technologies
Selected Publications
- S. B. Melhem, M. Golec, S. Alrabaee, M. Alshaikh, and M. Uyar,“EdgeAI-powered hybrid ESN-GRU model for high-accuracy and efficient short-term load forecasting in smart grids,”IEEE Access, vol. 13, pp. 198241–198251, 2025.
- S. B. Melhem, M. Golec, A. Alwarafy, and Y. Khamayseh, “LENS: Lightweight and explainable LLM-based APT detection at the edge for 6G security,” IEEE Access, vol. 13, pp. 172402–172415, 2025.
- M. Golec, Y. Khamayseh, S. B. Melhem, and A. Abdulmalik, “LLM-driven APT detection for 6G wireless networks: A systematic review and taxonomy,” IEEE Access, vol. 13, pp. 145271–145288, 2025.
- A. Alwarafy, S. B. Melhem, R. Abou Chahine, B. Said, and M. Alharethi, “Deep reinforcement learning-based joint trajectory design and resource allocation for secure and energy-efficient UAV networks,” IEEE Open Journal of the Communications Society, 2025.
- M. Alshaikh, Y. Alrajeh, S. Alamri, S. B. Melhem, and A. Abu-Khadrah, “Supervised methods of machine learning for email classification: A literature survey,” Systems Science & Control Engineering, vol. 13, no. 1, Art. no. 2474450, 2025.
- M. Ismail, N. T. Madathil, M. Alalawi, S. Alrabaee, M. I. Al Bataineh, and S. B. Melhem, “Cybersecurity activities for education and curriculum design: A survey,” Computers in Human Behavior Reports, vol. 16, Art. no. 100501, 2024.
- F. Alzhouri, S. B. Melhem, A. Agarwal, M. Daraghmeh, Y. Liu, and S. Younis, “Dynamic resource management for cloud spot markets,”
IEEE Access, vol. 8, pp. 122838–122847, 2020. - K. M. Addali, S. B. Melhem, Y. Khamayseh, Z. Zhang, and M. Kadoch, “Dynamic mobility load balancing for 5G small-cell networks based on utility functions,” IEEE Access, vol. 7, pp. 126998–127011, 2019.
- S. B. Melhem, A. Agarwal, N. Goel, and M. Zaman, “Markov prediction model for host load detection and VM placement in live migration,” IEEE Access, vol. 6, pp. 7190–7205, 2017.
- F. Belqasmi, J. Singh, S. Y. B. Melhem, and R. H. Glitho, “SOAP-based vs. RESTful web services: A case study for multimedia conferencing,” IEEE Internet Computing, vol. 16, no. 4, pp. 54–63, 2012.
Teaching Courses
- Computer Networks
- Intrusion Analysis and Incident Management
- Secure Programming
- Cybersecurity Law and Policy
- Computer Security Fundamentals
- Microprocessor and Assembly Language
- Introduction to Programming
Expertise related to UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all.
This person’s work contributes towards the following SDG(s):
EdgeAI-Powered Hybrid ESN-GRU Model for High-Accuracy and Efficient Short-Term Load Forecasting in Smart Grids
Published in: IEEE Access
Nov 11, 2025
With the widespread use of renewable energy sources (RES) in the smart grid, the next generation power system, short-term load forecasting (STLF) is of critical importance in grid stability and energy optimization. Traditional STLF models include issues such as high computational cost, dependency on cloud infrastructure, and latency issues, which are undesirable for real-time energy management. To solve these issues, the EdgeAI paradigm, which combines edge computing and artificial intelligence (AI), can be a promising solution. EdgeAI reduces the dependency on cloud-based systems by processing data close to the data source, offering advantages such as low latency and low bandwidth. Thus, it increases the response speed by processing data in real time, making it suitable for STLF applications. In order to benefit from all these advantages, the EdgeAI-driven Hybrid Echo State Network and Gated Recurrent Unit (ESN-GRU) model is introduced for real-time and efficient STLF in this paper. ESN-GRU combines the fast training capabilities of ESN and sequential learning capabilities of GRU, and offers the advantages of high prediction performance and low latency inference in STLF. Experimental results show that the proposed model improves the R2 score by 2.5% and significantly reduces the MAPE value from 129 to 0.101 compared to existing models. Benchmark results in edge environment prove that ESN-GRU provides up to 79% and 92% faster inference compared to state-of-the-art methods.
LENS: Lightweight and Explainable LLM-Based APT Detection at the Edge for 6G Security
Published in: IEEE Access
Sep 30, 2025
Expected to be deployed in the early 2030s, sixth-generation (6G) wireless networks, with their high speed and integration with cutting-edge technology such as intelligent edge computing, expand the attack surface and face serious cyber threat risks such as Advanced Persistent Threats (APTs). This type of cyber attack can imitate benign network traffic and operate for long periods of time without being detected by traditional detection systems. This paper introduces LENS, a lightweight and explainable LLM-based network security framework designed to address this cybersecurity threat for 6G environments. LENS uses a fine-tuned DistilBERT model to convert raw network streams into natural language commands using contextual metadata and is trained on the CICAPT-IIoT (2024) dataset generated using real-time network traffic data. To evaluate the proposed model, adapted versions of DeepLog and EarlyCrow are compared using F1-score, false positive rate, and explainability metrics for binary APT classification on the CICAPT-IIoT dataset. All models are trained using a high-performance GPU (Nvidia A10) and validated by deploying on a real-world resource-constrained edge node (Raspberry Pi 4). The results confirm that LENS has higher performance in APT detection with 0.82 accuracy and 0.82 recall despite consuming higher energy compared to the other two baselines, and is applicable for edge-enabled 6G environments.
LLM-Driven APT Detection for 6G Wireless Networks: A Systematic Review and Taxonomy
Published in: IEEE Access
Aug 05, 2025
Sixth Generation (6G) wireless networks, which are expected to be deployed in the 2030s, have already created great excitement in academia and the private sector with their extremely high communication speed and low latency rates. However, despite the ultra-low latency, high throughput, and AI-assisted orchestration capabilities they promise, they are vulnerable to stealthy and long-term Advanced Persistent Threats (APTs). Large Language Models (LLMs) stand out as an ideal candidate to fill this gap with their high success in semantic reasoning and threat intelligence. This paper presents the first systematic review and taxonomy for LLM-assisted APT detection in 6G networks. It also provides insights by reviewing recent research on the intersection of LLMs, APTs, and 6G. Key challenges such as limitations in edge deployment, data scarcities, and explainability gaps are identified and a multidimensional taxonomy is provided in line with the APT lifecycle and 6G contexts. The paper is based on 142 studies from 2018 to 2025, searching leading databases such as IEEE Xplore, ACM Digital Library, SpringerLink, and Elsevier ScienceDirect.
Deep Reinforcement Learning-Based Joint Trajectory Design and Resource Allocation for Secure and Energy-Efficient UAV Networks
Published in: IEEE Open Journal of the Communications Society
Aug 01, 2025
Unmanned Aerial Vehicles (UAVs) have been extensively used recently for wireless networks. However, such networks encounter several challenges that remain unsolved. In this paper, we address the issue of joint optimization of trajectory design and resource allocation in UAV-based wireless networks in the presence of eavesdroppers. We first formulate an optimization problem with the objective to maximize a utility function defined in terms of secrecy rate, energy utilization efficiency, and interference. Due to the high dimensionality and non-convex nature of the formulated problem, we propose a Proximal Policy Optimization (PPO)-based Deep Reinforcement Learning (DRL) algorithm to solve the problem and learn the environment. Our proposed PPO algorithm solves the problem by jointly controlling the 3D position of UAVs, power, and energy harvesting. Simulation results demonstrate the efficiency of the proposed algorithm in solving the problem, learning the environment dynamics, and its superiority over some existing conventional and DRL-based methods.
Supervised methods of machine learning for email classification: a literature survey
Published in: Systems Science & Control Engineering
May 15, 2025
In today’s digital landscape, email is acknowledged as a critical conduit for global data exchanges. With a surge in data volume, malefactors exploit user identities, leading to data misuse. Cybercriminals employ electronic transgressions such as phishing and spam to orchestrate security infractions. Machine learning counters these breaches using myriad techniques, demonstrating significant efficiency in identifying phishing emails. We can divide machine learning into two types: supervised and unsupervised. Supervised learning requires pre-training the model on labelled datasets, amalgamating classification, and regression learning. Notably, supervised methodologies such as support vector machines (SVMs), naive Bayes, decision trees, neural networks, random forests, and deep learning have been exploited for spam filtering. This review delves into issues concerning spam filtering and email classification through supervised machine learning techniques, offering a comprehensive evaluation of strategies, methods, performance indicators, and the benefits and drawbacks of different research. This information allows researchers to assess the efficiency and effectiveness of supervised learning algorithms, laying the foundation for advanced email categorization techniques.
Cybersecurity activities for education and curriculum design: A survey
Published in: Computers in Human Behavior Reports
Oct 21, 2024
Cyber threats are one of the main concerns in this growing technology epoch. To tackle this issue, highly skilled and motivated cybersecurity professionals are increasingly in demand to prevent, detect, respond to, or even mitigate the effects of such threats. However, the world faces a workforce shortage of qualified cybersecurity professionals and practitioners. To address this dilemma, several cybersecurity educational programs have been introduced, such as specialized cybersecurity courses in computer science graduate programs. With the increasing demand, different cybersecurity courses are introduced at the high school level, undergraduate computer science and information systems programs, and even at the government level. Due to the peculiar nature of cybersecurity, educational institutions face many issues when designing a curriculum or cybersecurity activities. In this paper, we study existing cybersecurity curriculum approaches and activities. We also present case studies on cybersecurity education around the globe.
Dynamic Resource Management for Cloud Spot Markets
Published in: IEEE Access
Jul 06, 2020
Resource management for cloud computing environments that are characterized by many layers emerges as a critical task for cloud computing providers. Such providers are compelled by the demands and strategies of stochastic customers to adopt dynamic resource management for the top-bottom scaling of the cloud resources on the basis of variable needs. Resource management in the infrastructure as a service layer relies on virtual machine (VM) characteristics, such as estimated VM classes. Given that a cloud provider offers a variety of VM classes that differ as regards the size of computing resources (e.g., central processing unit, memory, and input/output devices), optimizing cloud resources to maximize cloud revenue is a challenging dilemma. More specifically, the dynamic management of resources in cloud spot markets is confronted with various severe obstacles. In consideration of these issues, this study investigated a dynamic resource management model for cloud spot markets and put forward an efficient model that manages spare resources for the purpose of expanding cloud revenue. The model estimates the available spare capacity of a spot market, evaluates the maximum expected revenue of stagnant VMs on the basis estimated cumulative capacity, and locates the optimum VM combinations that bear complementary workloads and capacities and can coexist in a certain host. Our model also improves the understanding of cloud resource scaling and generates inferences that can be adopted in managing cloud resources for all layers as well as Reserved and On-Demand markets.
Dynamic mobility load balancing for 5G small-cell networks based on utility functions
Published in: IEEE Access
Sep 06, 2019
Deployment of small cells was introduced to support high data rate services and expand macro cell coverage for the envisioned 5G networks. A small cell network, which has a smaller size, along with the user equipment (UE) mobility, frequently undergoes unbalanced load status. Consequently, the network performance is affected in terms of throughput, increasing handover failure rate, and possibly higher link failure rate. Hence, load balancing has become an important part of recent researches on small cell networks. Mobility Load Balancing (MLB) involves load transfer from an overloaded small cell to under-loaded neighbouring small cells for the more load-balanced network. This transfer is performed by adjusting the handover parameters of the UEs according to the load situations of the small cells in the vicinity. However, inaccurate adjustment of parameters may lead to inefficient usage of network resources or degrade the Quality of Service (QoS). In this paper, we introduce a Utility-based Mobility Load Balancing algorithm (UMLB) and a new term named load balancing efficiency factor (LBEF). The UMLB algorithm considers the operator utility and the user utility for the MLB-based handover process. While LBEF is proposed to order the overloaded cells properly for the MLB algorithm operation. The simulation results show that the UMLB minimizes standard deviation with a higher average-UE data rate when compared to existing load balancing algorithms. Therefore, a well-balanced network is achieved.
Markov prediction model for host load detection and VM placement in live migration
Published in: IEEE Access
Dec 19, 2017
The design of good host overload/underload detection and virtual machine (VM) placement algorithms plays a vital role in assuring the smoothness of VM live migration. The presence of the dynamic environment that leads to a changing load on the VMs motivates us to propose a Markov prediction model to forecast the future load state of the host. We propose a host load detection algorithm to find the future overutilized/underutilized hosts state to avoid immediate VMs migration. Moreover, we propose a VM placement algorithm to determine the set of candidates hosts to receive the migrated VMs in a way to reduce their VM migrations in near future. We evaluate our proposed algorithms through CloudSim simulation on different types of PlanetLab real and random workloads. The experimental results show that our proposed algorithms have a significant reduction in terms of service-level agreement violation, the number of VM migrations, and other metrics than the other competitive algorithms.
Soap-based vs. restful web services: A case study for multimedia conferencing
Published in: IEEE internet computing
May 08, 2012
RESTful Web services are now emerging as an alternative to SOAP-based Web services and might be a more suitable choice in some cases. A comparison of two Web programming interfaces — the standard Parlay-X multimedia SOAP-based Web service and a RESTful Web service that offers the same functionalities — for developing multimedia conferencing applications shows that the RESTful Web interface offers better performance.