HRHafeez Ur Rehman

Hafeez Ur Rehman

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hafeez Ur Rehman has a total of 193 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    On the state of protein function prediction: a report on the fourth CAFA challenge

    by Rashika Ramola, M. Clara De Paolis Kaluza, Damiano Piovesan, Yisu Peng, Parnal Joshi, Mahta Mehdiabadi, Federica Quaglia, Rita Pancsa, Lucía B. Chemes, Hongryul Ahn, et al.

    Background: The Critical Assessment of Functional Annotation (CAFA) is a community effort held to understand the field of computational protein function prediction. Every three years, since 2010, the organizers initiate an experiment to collect function predictions on a large set of proteins and then evaluate the performance of predicting methods on a subset of proteins that have accumulated experimental annotations between the submission deadline and the evaluation time. CAFA provides an independent and rigorous assessment of the current state of the art, thus leveling the playing field, highlighting successes, revealing bottlenecks, and offering a forum for the exchange of ideas in protein science. Here, we report the results of the fourth CAFA experiment (CAFA4). Results: CAFA4 featured the participation of 148 methods from 70 research groups on a total of 46,205 unique proteins over a 5-year annotation accumulation phase, the longest in any CAFA. In a comparison across CAFA2-CAFA4 methods, the prediction of Gene Ontology (GO) terms has clearly improved across all three GO aspects and traditional evaluation settings. While not achieving the first rank, several CAFA2 and CAFA3 methods featured in the top ten methods in many evaluations, suggesting that earlier methods still hold relevance. The performance is weaker in the newly introduced “partial knowledge” evaluation category (proteins with experimental annotations before submission deadline that gained additional annotations in the same GO aspect during the annotation accumulation phase), highlighting the need for a new class of methods. The rankings of the methods were stable over the years in traditional evaluation settings, but less so in the new partial knowledge evaluation. Overall, the field continues to progress with some influx of new participants. Sustained efforts will be necessary to substantially advance it.

  • Open Access

    AI‐Driven IoT Botnet Detection: Strengthening Cybersecurity Through Advanced Machine Learning Techniques

    by Aysha Al-Naimi, Ali Baydoun, Moutaz Alazab, Hafeez Ur Rehman, Jihad AlJa’Am, Sumaya Al-Maadeed

    The rapid proliferation of internet of things (IoT) devices has dramatically expanded the cyberattack surface, enabling sophisticated botnets to compromise large numbers of interconnected endpoints for coordinated malicious campaigns. Traditional signature‐based defences are increasingly inadequate against these evolving threats, yet critical gaps remain in understanding how feature selection jointly optimises detection accuracy and computational efficiency across diverse botnet families under real‐world deployment constraints. This paper presents a systematic evaluation of random forest (RF) and decision tree (DT) classifiers for multi‐class IoT botnet detection using the N‐BaIoT dataset—a large‐scale benchmark comprising approximately 7.06 million network traffic instances from nine commercial IoT devices, spanning 115 features and 11 traffic classes, including Mirai and Bashlite/Gafgyt attack variants. An RF‐driven feature selection framework based on Gini impurity scoring was applied to reduce the feature space from 115 to the 35 most discriminative attributes, enabling rigorous preselection and post‐selection performance comparison. RF achieved 97.8% classification accuracy, and DT achieved 97.03%, with near‐perfect precision, recall and F1 scores across Mirai attack categories. Critically, feature reduction decreased computational overhead by approximately 2 min and 46 s while yielding a marginal accuracy gain, confirming that lightweight models can satisfy the real‐time constraints of resource‐limited IoT environments without sacrificing detection reliability. These results establish a scalable, interpretable ML framework for proactive IoT botnet defence, with direct implications for the design of efficient intrusion detection systems in large‐scale, heterogeneous IoT deployments.

  • Open Access

    IntruSafe: a FCNN-LSTM hybrid IoMT intrusion detection system for both string and 2D-spatial data using sandwich architecture

    by Moutaz Alazab, Albara Awajan, Areej Obeidat, Nuruzzaman Faruqui, Hafeez Ur Rehman

    The Internet of Medical Things (IoMT) is a resource-constrained device with limited computational capabilities. However, the market worth of this section is booming rapidly. The IoMT manufacturers need to offer their products at a competitive price, which forces them to use simplified architecture, leaving limited and, to some extent, no scope to employ sophisticated cybersecurity algorithms. As a result, IoMT has become a lucrative practice ground for cybercriminals. The IoMT sector deals with valuable, confidential healthcare-related data and offers convenient, personalized healthcare services. That is why the market demand and IoMT intrusion are experiencing massive growth. An innovative Intrusion Detection System (IDS), IntruSafe, has been studied, developed, and presented in this paper that combines Fully Connected Convolutional Neural Network (FCNN) and Long Short-Term Memory (LSTM) to protect the IoMT network from malicious signals. The IntruSafe combines FCNN and LSTM to ensure the detection of both malicious text and image data. It detects and simultaneously protects the IoMT network from further intrusion with only a 0.18% service interruption rate. This high-performing IDS detects intrusion with 97.66% accuracy, 98.50% precision, 97.33% recall, and 97.85% F1-score. With outstanding performance, IntruSafe is a promising IDS that will facilitate further growth of the IoMT sector while minimizing the risks of a successful intrusion.


  • Open Access

    Decoding MGMT Methylation: A Step Towards Precision Medicine in Glioblastoma

    by Hafeez Ur Rehman, Sumaiya Fazal, Moutaz Alazab, Ali Baydoun

    Glioblastomas, constituting over 50% of malignant brain tumors, are highly aggressive brain tumors that pose substantial treatment challenges due to their rapid progression and resistance to standard therapies. The methylation status of the O-6-Methylguanine-DNA Methyltransferase (MGMT) gene is a critical biomarker for predicting patient response to treatment, particularly with the alkylating agent temozolomide. However, accurately predicting MGMT methylation status using non-invasive imaging techniques remains challenging due to the complex and heterogeneous nature of glioblastomas, that includes, uneven contrast, variability within lesions, and irregular enhancement patterns. This study introduces the Convolutional Autoencoders for MGMT Methylation Status Prediction (CAMP) framework, which is based on adaptive sparse penalties to enhance predictive accuracy. The CAMP framework operates in two phases: first, generating synthetic MRI slices through a tailored autoencoder that effectively captures and preserves intricate tissue and tumor structures across different MRI modalities; second, predicting MGMT methylation status using a convolutional neural network enhanced by adaptive sparse penalties. The adaptive sparse penalty dynamically adjusts to variations in the data, such as contrast differences and tumor locations in MR images. Our method excels in MRI image synthesis, preserving brain tissue, fat, and individual tumor structures across all MRI modalities. Validated on benchmark datasets, CAMP achieved an accuracy of 0.97, specificity of 0.98, and sensitivity of 0.97, significantly outperforming existing methods. These results demonstrate the potential of the CAMP framework to improve the interpretation of MRI data and contribute to more personalized treatment strategies for glioblastoma patients.

  • Open Access

    PRONTO-TK: a user-friendly PROtein Neural neTwOrk tool-kit for accessible protein function prediction

    by Gianfranco Politano, Alfredo Benso, Hafeez Ur Rehman, Angela Re

    Associating one or more Gene Ontology (GO) terms to a protein means making a statement about a particular functional characteristic of the protein. This association provides scientists with a snapshot of the biological context of the protein activity. This paper introduces PRONTO-TK, a Python-based software toolkit designed to democratize access to Neural-Network based complex protein function prediction workflows. PRONTO-TK is a user-friendly graphical interface (GUI) for empowering researchers, even those with minimal programming experience, to leverage state-of-the-art Deep Learning architectures for protein function annotation using GO terms. We demonstrate PRONTO-TK’s effectiveness on a running example, by showing how its intuitive configuration allows it to easily generate complex analyses while avoiding the complexities of building such a pipeline from scratch.


  • Open Access

    Can Windows 11 Stop Well-Known Ransomware Variants? An Examination of Its Built-in Security Features

    by Yousef Mahmoud Al-Awadi, Ali Baydoun, Hafeez Ur Rehman

    The ever-evolving landscape of cyber threats, with ransomware at its forefront, poses significant challenges to the digital world. Windows 11 Pro, Microsoft’s latest operating system, claims to offer enhanced security features designed to tackle such threats. This paper aims to comprehensively evaluate the effectiveness of these Windows 11 Pro, built-in security measures against prevalent ransomware strains, with a particular emphasis on crypto-ransomware. Utilizing a meticulously crafted experimental environment, the research adopted a two-phased testing approach, examining both the default and a hardened configuration of Windows 11 Pro. This dual examination offered insights into the system’s inherent and potential defenses against ransomware threats. The study’s findings revealed that Windows 11 Pro does present formidable defenses. This paper not only contributes valuable insights into cybersecurity, but also furnishes practical recommendations for both technology developers and end-users in the ongoing battle against ransomware. The significance of these findings extends beyond the immediate evaluation of Windows 11 Pro, serving as a reference point for the broader discourse on enhancing digital security measures.


  • Open Access

    CapGAN: Text-to-Image Synthesis Using Capsule GANs

    by Maryam Omar, Hafeez Ur Rehman, Omar Bin Samin, Moutaz Alazab, Gianfranco Politano, Alfredo Benso

    Text-to-image synthesis is one of the most critical and challenging problems of generative modeling. It is of substantial importance in the area of automatic learning, especially for image creation, modification, analysis and optimization. A number of works have been proposed in the past to achieve this goal; however, current methods still lack scene understanding, especially when it comes to synthesizing coherent structures in complex scenes. In this work, we propose a model called CapGAN, to synthesize images from a given single text statement to resolve the problem of global coherent structures in complex scenes. For this purpose, skip-thought vectors are used to encode the given text into vector representation. This encoded vector is used as an input for image synthesis using an adversarial process, in which two models are trained simultaneously, namely: generator (G) and discriminator (D). The model G generates fake images, while the model D tries to predict what the sample is from training data rather than generated by G. The conceptual novelty of this work lies in the integrating capsules at the discriminator level to make the model understand the orientational and relative spatial relationship between different entities of an object in an image. The inception score (IS) along with the Fréchet inception distance (FID) are used as quantitative evaluation metrics for CapGAN. IS recorded for images generated using CapGAN is 4.05 ± 0.050, which is around 34% higher than images synthesized using traditional GANs, whereas the FID score calculated for synthesized images using CapGAN is 44.38, which is ab almost 9% improvement from the previous state-of-the-art models. The experimental results clearly demonstrate the effectiveness of the proposed CapGAN model, which is exceptionally proficient in generating images with complex scenes.