Mah-Rukh Fida
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mah-Rukh Fida has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Ahmed Elmokashfi
Simula Metropolitan Center for Digital Engineering, Oslo, Norway
4 shared publications - Azza H. Ahmed
Oslo Metropolitan University
4 shared publications - Ameer Shakayb Arsalaan
University of Swabi
3 shared publications - Andres F. Ocampo
SimulaMet—Simula Metropolitan Center for Digital Engineering, 0167 Oslo, Norway
3 shared publications Ahmed Elmokashfi
1 shared publication- Ahmed Elmokashfi
Amazon Web Services (AWS), Seattle, WA 98109, USA
1 shared publication
Latest Publications
- Open Access
- 25 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (11) , 5267
5G and Beyond: Technologies and Communications
The rapid evolution of fifth-generation (5G) and beyond-fifth-generation (B5G) wireless technologies is transforming the way societies connect, communicate, and interact with digital services
- 25 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (11) , 5267
Open Access5G and Beyond: Technologies and Communications
The rapid evolution of fifth-generation (5G) and beyond-fifth-generation (B5G) wireless technologies is transforming the way societies connect, communicate, and interact with digital services
- Open Access
- 14 March 2026
- Published by Elsevier in Computer Networks
- Vol. 281
Leveraging programmable data plane for network intrusion detection: A survey
- 14 March 2026
- Published by Elsevier in Computer Networks
- Vol. 281
Open AccessLeveraging programmable data plane for network intrusion detection: A survey
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 174585-174604
In-Network Security Framework for Detecting and Classifying DDoS Attacks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 174585-174604
Open AccessIn-Network Security Framework for Detecting and Classifying DDoS Attacks
- Open Access
- 1 January 2026
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2026 (1) , 6908869
Blockchain‐Based AI Intelligent Systems in Healthcare: A Decentralized Federated Learning Framework With Zero Trust
Artificial intelligence (AI), blockchain (BC), and federated learning (FL) offer significant potential for strengthening data privacy, security, and decentralized decision‐making in healthcare. However, healthcare AI systems remain vulnerable to adversarial threats, including data poisoning, Byzantine behavior, Sybil attacks, and unauthorized access. This article provides an integrative review of the pertinent literature from which a conceptual framework for exploring the relationship between BC, FL, and Zero Trust (ZT) is developed in the context of AI in healthcare. An experimental framework for a ZT approach based on BC and FL is then designed, tested, and evaluated. The framework combines strict identity verification, permissioned BC access control, immutable auditability, decentralized model training, and history‐aware threat detection to enhance robustness while preserving data privacy. A series of simulations was conducted to evaluate the framework under poisoning, Byzantine, and Sybil attack scenarios, using F 1‐score as the primary model‐performance metric and latency, gas cost, and throughput as BC‐performance metrics. The results show that poisoning clients were consistently detected and excluded once adversarial behavior began, with only minor temporary performance degradation and subsequent recovery of global model performance. Under Byzantine attacks, the proposed history‐aware trust filter improved the global F 1‐score across evaluated configurations, including an increase from 0.7762 under attack to 0.9117 with defense in one configuration. BC operations remained efficient, with latency generally between approximately 19 and 39 ms and throughput of 31.65 transactions per second, although upload operations incurred the highest gas cost. Sybil attack experiments further confirmed that cryptographic identity verification and permissioned access control prevented malicious identities from affecting the FL process, while attack cost increased linearly with no operational gain. The findings demonstrate that the proposed framework can effectively balance privacy preservation, adversarial robustness, auditability, and performance, making it a promising approach for secure healthcare systems.
- 1 January 2026
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2026 (1) , 6908869
Open AccessBlockchain‐Based AI Intelligent Systems in Healthcare: A Decentralized Federated Learning Framework With Zero Trust
Artificial intelligence (AI), blockchain (BC), and federated learning (FL) offer significant potential for strengthening data privacy, security, and decentralized decision‐making in healthcare. However, healthcare AI systems remain vulnerable to adversarial threats, including data poisoning, Byzantine behavior, Sybil attacks, and unauthorized access. This article provides an integrative review of the pertinent literature from which a conceptual framework for exploring the relationship between BC, FL, and Zero Trust (ZT) is developed in the context of AI in healthcare. An experimental framework for a ZT approach based on BC and FL is then designed, tested, and evaluated. The framework combines strict identity verification, permissioned BC access control, immutable auditability, decentralized model training, and history‐aware threat detection to enhance robustness while preserving data privacy. A series of simulations was conducted to evaluate the framework under poisoning, Byzantine, and Sybil attack scenarios, using F 1‐score as the primary model‐performance metric and latency, gas cost, and throughput as BC‐performance metrics. The results show that poisoning clients were consistently detected and excluded once adversarial behavior began, with only minor temporary performance degradation and subsequent recovery of global model performance. Under Byzantine attacks, the proposed history‐aware trust filter improved the global F 1‐score across evaluated configurations, including an increase from 0.7762 under attack to 0.9117 with defense in one configuration. BC operations remained efficient, with latency generally between approximately 19 and 39 ms and throughput of 31.65 transactions per second, although upload operations incurred the highest gas cost. Sybil attack experiments further confirmed that cryptographic identity verification and permissioned access control prevented malicious identities from affecting the FL process, while attack cost increased linearly with no operational gain. The findings demonstrate that the proposed framework can effectively balance privacy preservation, adversarial robustness, auditability, and performance, making it a promising approach for secure healthcare systems.
- Open Access
- 31 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 136446-136457
IoTShield: Defending IoT Systems Against Prevalent Attacks Using Programmable Networks
The growing proliferation of Internet of Things (IoT) devices in smart homes, smart agriculture, and smart energy grids has greatly improved their functionality, efficiency, and responsiveness — but it has also widened the attack surface of these networks. The inherent security vulnerabilities of IoT devices, have rendered them susceptible to a variety of flow-based attacks such as Distributed Denial of Service (DDoS), scanning, spoofing, data exfiltration and web-based attacks, thereby diminishing their potential benefits. This paper presents IoTShield, a Software Defined Network (SDN) based dual-stage defensive framework, designed to mitigate different flow-based attacks targeting IoT systems. Leveraging recent advancements in programmable networks, our defensive framework enables each programmable switch within the connectivity layer of the network to be responsible of identifying a single attack category among prevalent attacks. Furthermore, to effectively mitigate the spread of these attacks, detected attacks are classified at the network controller, facilitating timely updates to the data plane defensive rules. As a proof of concept, using CICIoT2023 dataset, we first illustrate that deploying separate detectors for DDoS and Web-based attack categories on programmable data planes reduces false alarms by 58% and 97%, respectively. Furthermore, a single DDoS attacks detector based on lightweight Decision Tree (DT) model in the data plane, achieves 80-99% of accuracy in detecting different types of attack flows, with fine-grained classification offloaded to the control plane where a Convolutional Neural Network (CNN) classifier achieves 99% accuracy. Besides, IoTShield significantly reduces the latency and load on controller to perform the attack detection; with only 0.14 milliseconds of additional median queuing delay.
- 31 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 136446-136457
Open AccessIoTShield: Defending IoT Systems Against Prevalent Attacks Using Programmable Networks
The growing proliferation of Internet of Things (IoT) devices in smart homes, smart agriculture, and smart energy grids has greatly improved their functionality, efficiency, and responsiveness — but it has also widened the attack surface of these networks. The inherent security vulnerabilities of IoT devices, have rendered them susceptible to a variety of flow-based attacks such as Distributed Denial of Service (DDoS), scanning, spoofing, data exfiltration and web-based attacks, thereby diminishing their potential benefits. This paper presents IoTShield, a Software Defined Network (SDN) based dual-stage defensive framework, designed to mitigate different flow-based attacks targeting IoT systems. Leveraging recent advancements in programmable networks, our defensive framework enables each programmable switch within the connectivity layer of the network to be responsible of identifying a single attack category among prevalent attacks. Furthermore, to effectively mitigate the spread of these attacks, detected attacks are classified at the network controller, facilitating timely updates to the data plane defensive rules. As a proof of concept, using CICIoT2023 dataset, we first illustrate that deploying separate detectors for DDoS and Web-based attack categories on programmable data planes reduces false alarms by 58% and 97%, respectively. Furthermore, a single DDoS attacks detector based on lightweight Decision Tree (DT) model in the data plane, achieves 80-99% of accuracy in detecting different types of attack flows, with fine-grained classification offloaded to the control plane where a Convolutional Neural Network (CNN) classifier achieves 99% accuracy. Besides, IoTShield significantly reduces the latency and load on controller to perform the attack detection; with only 0.14 milliseconds of additional median queuing delay.
- Open Access
- 2 July 2025
- Published by Sohail Altaf Printers in International Journal of Pathology
- Vol. 23 (2) , 98-104
Waist-to-height ratio and body roundness index as predictors of insulin resistance in Pakistani adults
Background: A major risk factor for metabolic syndrome and type 2 diabetes mellitus (T2DM), insulin resistance (IR) is especially common in South Asian populations. One of the main causes of IR, central adiposity, is not well represented by traditional anthropometric measures such as the body mass index (BMI) and waist-to-hip ratio (WHR). Using gender- and age-stratified analyses, this study examines the diagnostic value of the Waist-to-Height Ratio (WtHR) and Body Roundness Index (BRI) in predicting IR in Pakistani adults. Methods: In this cross-sectional study, 1,592 adults aged 18–70 years were recruited from tertiary care hospitals in Peshawar, Pakistan. IR was defined with a threshold of >2.5 using the Homeostasis Model Assessment of Insulin Resistance (HOMA-IR). WtHR, BRI, BMI, WHR, and Abdominal Volume Index (AVI) were calculated using anthropometric data (height, weight, and waist circumference). Youden Index (J) and Receiver Operating Characteristic (ROC) curves were used to assess diagnostic performance, with subgroup analysis by age (≥60 years vs. ≥60 years) and gender. Results: WtHR showed the highest area under the curve (AUC = 0.710), followed by BRI (AUC = 0.707). The optimal cut-off for WtHR (0.54) achieved 71% sensitivity and 69% specificity (J = 0.40), while BRI (cut-off: 4.2) yielded 69% sensitivity and 68% specificity (J = 0.37). Conclusion: WtHR and BRI are better at predicting insulin resistance than traditional indices, especially in younger and female populations. In resource limited environments, such as Pakistan, their non-invasive nature and ease of use make them useful instruments for early IR screening.
- 2 July 2025
- Published by Sohail Altaf Printers in International Journal of Pathology
- Vol. 23 (2) , 98-104
Open AccessWaist-to-height ratio and body roundness index as predictors of insulin resistance in Pakistani adults
Background: A major risk factor for metabolic syndrome and type 2 diabetes mellitus (T2DM), insulin resistance (IR) is especially common in South Asian populations. One of the main causes of IR, central adiposity, is not well represented by traditional anthropometric measures such as the body mass index (BMI) and waist-to-hip ratio (WHR). Using gender- and age-stratified analyses, this study examines the diagnostic value of the Waist-to-Height Ratio (WtHR) and Body Roundness Index (BRI) in predicting IR in Pakistani adults. Methods: In this cross-sectional study, 1,592 adults aged 18–70 years were recruited from tertiary care hospitals in Peshawar, Pakistan. IR was defined with a threshold of >2.5 using the Homeostasis Model Assessment of Insulin Resistance (HOMA-IR). WtHR, BRI, BMI, WHR, and Abdominal Volume Index (AVI) were calculated using anthropometric data (height, weight, and waist circumference). Youden Index (J) and Receiver Operating Characteristic (ROC) curves were used to assess diagnostic performance, with subgroup analysis by age (≥60 years vs. ≥60 years) and gender. Results: WtHR showed the highest area under the curve (AUC = 0.710), followed by BRI (AUC = 0.707). The optimal cut-off for WtHR (0.54) achieved 71% sensitivity and 69% specificity (J = 0.40), while BRI (cut-off: 4.2) yielded 69% sensitivity and 68% specificity (J = 0.37). Conclusion: WtHR and BRI are better at predicting insulin resistance than traditional indices, especially in younger and female populations. In resource limited environments, such as Pakistan, their non-invasive nature and ease of use make them useful instruments for early IR screening.
- 7 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (3) , 4877-4892
UAVs Relay in Emergency Communications With Strict Requirements on Quality of Information
Mobile Ad-hoc Networks (MANETs) are increasingly being used to provide communications in emergencies. Maintaining the required quality of service of information including its timely delivery, in MANETs, is extremely challenging under dynamic conditions such as a changing bushfire scenario. Nodes get destroyed or their link qualities degrade leading to sub-optimal paths, reduced network performance, and disconnected end nodes. To remedy partitioning in ground-based MANETs and to improve their communication performance, Unmanned Aerial Vehicles (UAVs) have emerged as a promising relay solution. This paper presents U-QoIT, a UAV deployment algorithm for connecting the disconnected end nodes in a dynamic bushfire scenario. It aims to meet the Quality of Information requirements, with a minimal number of UAVs deployed. U-QoIT takes the UAV deployment problem as a combinatorial search problem and reduces the deployment complexity by applying a reduction by minimization approach. This is done to deploy fewer UAVs without compromising connectivity. Extensive simulation results depict that U-QoIT significantly improves user usability by 48% compared to the best-performing baseline approach, of Dynamic Service Area (DSA) based UAV deployment, at the expense of a negligible increase in computational time. It achieves a 38% drop in packet latency and retains its out-performance in a highly mobile network. In a sparse network, it improves user usability by 106%. Furthermore, it needs fewer UAVs, compared to the baseline UAV deployment methods, without compromising its performance gains.
- 7 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 74 (3) , 4877-4892
UAVs Relay in Emergency Communications With Strict Requirements on Quality of Information
Mobile Ad-hoc Networks (MANETs) are increasingly being used to provide communications in emergencies. Maintaining the required quality of service of information including its timely delivery, in MANETs, is extremely challenging under dynamic conditions such as a changing bushfire scenario. Nodes get destroyed or their link qualities degrade leading to sub-optimal paths, reduced network performance, and disconnected end nodes. To remedy partitioning in ground-based MANETs and to improve their communication performance, Unmanned Aerial Vehicles (UAVs) have emerged as a promising relay solution. This paper presents U-QoIT, a UAV deployment algorithm for connecting the disconnected end nodes in a dynamic bushfire scenario. It aims to meet the Quality of Information requirements, with a minimal number of UAVs deployed. U-QoIT takes the UAV deployment problem as a combinatorial search problem and reduces the deployment complexity by applying a reduction by minimization approach. This is done to deploy fewer UAVs without compromising connectivity. Extensive simulation results depict that U-QoIT significantly improves user usability by 48% compared to the best-performing baseline approach, of Dynamic Service Area (DSA) based UAV deployment, at the expense of a negligible increase in computational time. It achieves a 38% drop in packet latency and retains its out-performance in a highly mobile network. In a sparse network, it improves user usability by 106%. Furthermore, it needs fewer UAVs, compared to the baseline UAV deployment methods, without compromising its performance gains.
- Open Access
Assessing the Cloud-RAN in the Linux Kernel: Sharing Computing and Network Resources
Cloud-based Radio Access Network (Cloud-RAN) leverages virtualization to enable the coexistence of multiple virtual Base Band Units (vBBUs) with collocated workloads on a single edge computer, aiming for economic and operational efficiency. However, this coexistence can cause performance degradation in vBBUs due to resource contention. In this paper, we conduct an empirical analysis of vBBU performance on a Linux RT-Kernel, highlighting the impact of resource sharing with user-space tasks and Kernel threads. Furthermore, we evaluate CPU management strategies such as CPU affinity and CPU isolation as potential solutions to these performance challenges. Our results highlight that the implementation of CPU affinity can significantly reduce throughput variability by up to 40%, decrease vBBU’s NACK ratios, and reduce vBBU scheduling latency within the Linux RT-Kernel. Collectively, these findings underscore the potential of CPU management strategies to enhance vBBU performance in Cloud-RAN environments, enabling more efficient and stable network operations. The paper concludes with a discussion on the efficient realization of Cloud-RAN, elucidating the benefits of implementing proposed CPU affinity allocations. The demonstrated enhancements, including reduced scheduling latency and improved end-to-end throughput, affirm the practicality and efficacy of the proposed strategies for optimizing Cloud-RAN deployments.
Open AccessAssessing the Cloud-RAN in the Linux Kernel: Sharing Computing and Network Resources
Cloud-based Radio Access Network (Cloud-RAN) leverages virtualization to enable the coexistence of multiple virtual Base Band Units (vBBUs) with collocated workloads on a single edge computer, aiming for economic and operational efficiency. However, this coexistence can cause performance degradation in vBBUs due to resource contention. In this paper, we conduct an empirical analysis of vBBU performance on a Linux RT-Kernel, highlighting the impact of resource sharing with user-space tasks and Kernel threads. Furthermore, we evaluate CPU management strategies such as CPU affinity and CPU isolation as potential solutions to these performance challenges. Our results highlight that the implementation of CPU affinity can significantly reduce throughput variability by up to 40%, decrease vBBU’s NACK ratios, and reduce vBBU scheduling latency within the Linux RT-Kernel. Collectively, these findings underscore the potential of CPU management strategies to enhance vBBU performance in Cloud-RAN environments, enabling more efficient and stable network operations. The paper concludes with a discussion on the efficient realization of Cloud-RAN, elucidating the benefits of implementing proposed CPU affinity allocations. The demonstrated enhancements, including reduced scheduling latency and improved end-to-end throughput, affirm the practicality and efficacy of the proposed strategies for optimizing Cloud-RAN deployments.
- Open Access
- 5 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (5) , 5660-5676
Bottleneck Identification in Cloudified Mobile Networks Based on Distributed Telemetry
Cloudified mobile networks are expected to deliver a multitude of services with reduced capital and operating expenses. A characteristic example is 5G networks serving several slices in parallel. Such mobile networks, therefore, need to ensure that the SLAs of customised end-to-end sliced services are met. This requires monitoring the resource usage and characteristics of data flows at the virtualised network core, as well as tracking the performance of the radio interfaces and UEs. A centralised monitoring architecture can not scale to support millions of UEs though. This paper, proposes a 2-stage distributed telemetry framework in which UEs act as early warning sensors. After UEs flag an anomaly, a ML model is activated, at network controller, to attribute the cause of the anomaly. The framework achieves 85% F1-score in detecting anomalies caused by different bottlenecks, and an overall 89% F1-score in attributing these bottlenecks. This accuracy of our distributed framework is similar to that of a centralised monitoring system, but with no overhead of transmitting UE-based telemetry data to the centralised controller. The study also finds that passive in-band network telemetry has the potential to replace active monitoring and can further reduce the overhead of a network monitoring system.
- 5 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (5) , 5660-5676
Open AccessBottleneck Identification in Cloudified Mobile Networks Based on Distributed Telemetry
Cloudified mobile networks are expected to deliver a multitude of services with reduced capital and operating expenses. A characteristic example is 5G networks serving several slices in parallel. Such mobile networks, therefore, need to ensure that the SLAs of customised end-to-end sliced services are met. This requires monitoring the resource usage and characteristics of data flows at the virtualised network core, as well as tracking the performance of the radio interfaces and UEs. A centralised monitoring architecture can not scale to support millions of UEs though. This paper, proposes a 2-stage distributed telemetry framework in which UEs act as early warning sensors. After UEs flag an anomaly, a ML model is activated, at network controller, to attribute the cause of the anomaly. The framework achieves 85% F1-score in detecting anomalies caused by different bottlenecks, and an overall 89% F1-score in attributing these bottlenecks. This accuracy of our distributed framework is similar to that of a centralised monitoring system, but with no overhead of transmitting UE-based telemetry data to the centralised controller. The study also finds that passive in-band network telemetry has the potential to replace active monitoring and can further reduce the overhead of a network monitoring system.
- 10 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 20 (3) , 2201-2217
Opportunistic CPU Sharing in Mobile Edge Computing Deploying the Cloud-RAN
Leveraging virtualization technology, Cloud-RAN deploys multiple virtual Base Band Units (vBBUs) along with collocated applications on the same Mobile Edge Computing (MEC) server. However, the performance of real-time (RT) applications such as the vBBU could potentially be impacted by sharing computing resources with collocated workloads. To address this challenge, this paper presents a dynamic CPU sharing mechanism, specifically designed for containerized virtualization in MEC servers, that hosts both RT and non-RT general-purpose applications. Initially, the CPU sharing problem in MEC servers is formulated as a Mixed-Integer Programming (MIP). Then, we present an algorithmic solution that breaks down the MIP into simpler subproblems that are then solved using efficient, constant factor heuristics. We assessed the performance of this mechanism against instances of a commercial solver. Further, via a small-scale testbed, we assessed various CPU sharing mechanisms and their effectiveness in reducing the impact of CPU sharing on RT application processing performance. Our findings indicate that our CPU sharing mechanism reduces the worst-case execution time by more than 150% compared to the default host RT-Kernel approach. This evidence is strengthened when evaluating this mechanism within Cloud-RAN, in which vBBUs share resources with collocated applications on a MEC server. Using our CPU sharing approach, the vBBU’s scheduling latency decreases by up to 21% in comparison with the host RT-Kernel.
- 10 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 20 (3) , 2201-2217
Opportunistic CPU Sharing in Mobile Edge Computing Deploying the Cloud-RAN
Leveraging virtualization technology, Cloud-RAN deploys multiple virtual Base Band Units (vBBUs) along with collocated applications on the same Mobile Edge Computing (MEC) server. However, the performance of real-time (RT) applications such as the vBBU could potentially be impacted by sharing computing resources with collocated workloads. To address this challenge, this paper presents a dynamic CPU sharing mechanism, specifically designed for containerized virtualization in MEC servers, that hosts both RT and non-RT general-purpose applications. Initially, the CPU sharing problem in MEC servers is formulated as a Mixed-Integer Programming (MIP). Then, we present an algorithmic solution that breaks down the MIP into simpler subproblems that are then solved using efficient, constant factor heuristics. We assessed the performance of this mechanism against instances of a commercial solver. Further, via a small-scale testbed, we assessed various CPU sharing mechanisms and their effectiveness in reducing the impact of CPU sharing on RT application processing performance. Our findings indicate that our CPU sharing mechanism reduces the worst-case execution time by more than 150% compared to the default host RT-Kernel approach. This evidence is strengthened when evaluating this mechanism within Cloud-RAN, in which vBBUs share resources with collocated applications on a MEC server. Using our CPU sharing approach, the vBBU’s scheduling latency decreases by up to 21% in comparison with the host RT-Kernel.