Zeeshan Ali

Dr. Zeeshan Ali

DISIM, Università degli studi dell'Aquila, L’Aquila, Abruzzo, Italy
+1
orcid
Cyber Security Researcher

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 September 2024 in IEEE Access
Verified
Journal Article
Open access
Zeeshan AliZeeshan Ali
Zeeshan Ali
WTWalter Tiberti
Walter Tiberti
Andrea MarottaAndrea Marotta
Andrea Marotta
DCDajana Cassioli
Dajana Cassioli
Intrusion detection systems (IDS) stand as formidable guardians in network security, playing a pivotal role in identifying and mitigating potential threats. As our digital landscape evolves, the imperative for robust intrusion detection mechanisms grows exponentially. The significance of IDS extends beyond preserving the integrity, confidentiality, and availability of network resources. In the dynamic realm of evolving cyber threats, IDS acts as the frontline defender-constantly monitoring network traffic to pinpoint suspicious activities and preemptively mitigate security breaches. In this paper, we study the effectiveness of combining the potency of the transformer-based model known as Bidirectional Encoder Representations from Transformers (BERT) in conjunction with the Synthetic Minority Over-sampling Technique (SMOTE) and a Multi-Layer Perceptron (MLP) to enhance the classification tasks in Machine Learning (ML) based IDS. We tested our approach on well-known and recent datasets, demonstrating that it is possible to obtain very high accuracy and robust performance in the detection of various attack types even when the datasets are affected by class imbalance. Beyond these results, our research introduces a novel perspective by seamlessly integrating the interpretability and context awareness of BERT with the efficient classification of MLP. This novel approach holds promise for advancing intrusion detection capabilities and contributing to the broader cybersecurity community.

11 August 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Open access
Zeeshan AliZeeshan Ali
Zeeshan Ali
WTWalter Tiberti
Walter Tiberti
Andrea MarottaAndrea Marotta
Andrea Marotta
DCDajana Cassioli
Dajana Cassioli
The rapidly evolving landscape of cyber threats poses significant challenges to network security, particularly in decentralized environments such as edge computing. This paper proposes an enhanced Intrusion Detection System (IDS) architecture that integrates Transfer Learning (TL) to create a unified supermodel, enabling adaptability and scalability for detecting emerging threats across diverse datasets. The key contributions of this study include: (1) leveraging BERT-based feature extraction to enhance the semantic understanding of intrusion patterns, (2) employing an MLP classifier refined through TL to improve classification performance (3) addressing class imbalance using Synthetic Minority Over-Sampling Technique (SMOTE), and (4) optimizing model deployment by distributing the heaviest computational tasks for the creation of the unified supermodel across the edge nodes with the available capacity, thereby reducing latency and enabling accurate real-time threat detection by resource constrained IoT devices. The proposed TL-enabled supermodel is periodically updated and shared with the IoT devices, ensuring robust and adaptive security mechanisms without the need for extensive local training. Our experimental evaluation on CIC-IDS 2017 and NSL-KDD 2009 datasets demonstrates the effectiveness of the approach, achieving 99% accuracy, precision, recall, and F1-score. Our results highlight the scalability, efficiency, and real-world applicability of our IDS framework, reinforcing its role in fortifying network security within highly dynamic cyber threat landscapes.

22 September 2024 in VFAST Transactions on Software Engineering
Verified
Journal Article
Open access
PDF file
MHMuhammad Adnan Hasnain
Muhammad Adnan Hasnain
Zeeshan AliZeeshan Ali
Zeeshan Ali
MMMuhammad Sajid Maqbool
Muhammad Sajid Maqbool
MAMusfira Aziz
Musfira Aziz
Dental cavities are a highly common persistent dental problem that impacts populations across different age groups on a global scale. It is crucial to get a dental issue diagnosed as early as possible and with as much accuracy as possible to treat it efficiently and prevent any related issues. If a dental infection is not treated, it will eventually grow and cause tooth loss. Dental X-ray images are crucial and beneficial in the diagnostic process of dental diseases for dentists. By applying Deep Learning (DL) techniques to dental X-ray images, dental experts can efficiently and precisely detect dental conditions, including dental cavities, fillings and implants. The objective of this research is to assess the performance of DL-based methods for dental disease detection via panoramic radiographs. In this study, we evaluated the performance of all of the EfficientNet variants (e.g., EfficientNets B0-B7) to determine which one is the most effective model for detecting dental disease. Moreover, we utilized the Borderline Synthetic Minority Oversampling Technique (SMOTE) to cope with the issue related to the minority classes contained in the dataset. To assess the efficacy of the model, various metrics are employed, including recall, accuracy, precision, loss, and F1-score. As a result, the performance of the EfficientNet-B5 model was superior to that of the other EfficientNet models. The EfficientNet-B5 model achieved the following values for its metrics: F1-score, accuracy, recall, AUC, and precision: 98.37%, 98.32%, 98.32%, 99.21%, and 98.32%, respectively. The accuracy rates for the EfficientNet-B0, EfficientNet-B1, EfficientNet-B2, EfficientNet-B3, EfficientNet-B4, EfficientNet-B6, and EfficientNet-B7, are 91.59%, 94.12%, 93.28%, 85.71%, 94.96%, 96.64% and 90.76%, respectively. The results indicated that the EfficientNet-B5 model performs better than other EfficientNet classifiers, which supports dental professionals significantly in the recognition of dental diseases.

27 October 2025
Verified
Conference Paper
Closed access
Zeeshan AliZeeshan Ali
Zeeshan Ali
AMA. Marotta
A. Marotta
WTW. Tiberti
W. Tiberti
OOO. Odoardi
O. Odoardi
DCD. Cassioli
D. Cassioli
PMP. Di Marco
P. Di Marco
Intrusion Detection Systems (IDS) are pivotal in securing Industrial Internet of Things (IIoT) networks, where the convergence of operational technology (OT) and information technology (IT) has heightened vulnerability to sophisticated cyber threats. The complexity, scale, and heterogeneity of IIoT environments necessitate advanced threat detection mechanisms capable of identifying and mitigating attacks in real-time. In this study, we propose a novel deep learning-based IDS framework that integrates Google BERT for advanced feature extraction and a Multi-Layer Perceptron (MLP) for robust classification. Our methodology is evaluated using three IIoT-specific benchmark datasets: CIC APT IIoT 2024, WUSTL IIoT 2021, and WUSTL IIoT 2018, which encompass diverse attack scenarios and network behaviors. To address the prevalent issue of class imbalance in these datasets, we employ the Synthetic Minority Over-sampling Technique (SMOTE), enhancing the model’s ability to learn and generalize minority attack patterns effectively. Experimental results demonstrate that our proposed framework significantly improves the detection accuracy of cyber threats in IIoT environments. The system’s scalability, efficiency, and real-time applicability make it a promising solution for safeguarding OT networks against evolving cyber threats. This study provides a practical and high-performance approach to enhancing the resilience of IIoT ecosystems.

3 May 2025 in VFAST Transactions on Software Engineering
Verified
Journal Article
Open access
PDF file
Zeeshan AliZeeshan Ali
Zeeshan Ali
AAAdnan Akram
Adnan Akram
Naeem AslamNaeem Aslam
Naeem Aslam
MKMuhammad Saeed Khurram
Muhammad Saeed Khurram
Intrusion detection systems (IDS) serve as critical sentinels in network security, assuming a paramount role in identifying and mitigating potential threats. With the evolution of our digital landscape, robust and productive intrusion detection mechanisms have become increasingly imperative. The significance of IDS lies in their ability to safeguard network resources’ integrity, confidentiality, and availability. In an era where cyber threats constantly evolve in complexity and scale, IDS serves as the front line of defence, tirelessly monitoring network traffic to pinpoint suspicious activities and mitigate potential security breaches. To address the class imbalance problem, the Synthetic Minority Over-sampling Technique (SMOTE) was applied to pre-process the CIC-IDS 2017 and NSL-KDD 2009 datasets. Advanced machine learning technique is harnessed to enhance IDS capabilities, specifically through utilising Support Vector Machines (SVM) for subsequent classification tasks. The experimental outcomes on both datasets unveil exceptional accuracy of 99% and performance across multiple intrusion types, underscoring the effectiveness of our SVM-based approach in strengthening IDS.

24 August 2025
Verified
Conference Paper
Closed access
Zeeshan AliZeeshan Ali
Zeeshan Ali
WTWalter Tiberti
Walter Tiberti
AMAndrea Marotta
Andrea Marotta
DCDajana Cassioli
Dajana Cassioli
This paper aims to tackle the cyber threats posed by decentralized settings, such as edge computing, by exploiting the Transfer Learning (TL) approach to create a lightweight Intrusion Detection System (IDS) for resource-constrained IoT devices. The proposed approach shifts the training complexity to the edge, allowing resource-constrained IoT devices to use less resources because they receive from the edge a single (unified) pre-trained supermodel. This supermodel ensures real-time adaptability across multiple datasets and edge environments and achieves 99% accuracy, precision, recall, and F1-score, while reducing latency and increasing scalability. Beyond TL, the proposed approach combines BERT-based semantic feature extraction, MLP classification, and SMOTE class imbalance compensation for improved performance.