arXiv subjects

Nour Moustafa

Publications and source records attributed to Nour Moustafa.

At least 19 recordsLinked to original sources

arXiv2026

Progressive Split Mamba: Effective State Space Modelling for Image Restoration

Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic complexity for global attention, recent State Space Models (SSMs), such as Mamba, provide an appealing linear-time alternative for long-range dependency modelling. However, naively extending Mamba to 2D images exposes two intrinsic shortcomings. First, flattening 2D feature maps into 1D sequences disrupts spatial topology, leading to locality distortion that hampers precise structural recovery. Second, the stability-driven recurrent dynamics of SSMs induce long-range decay, progressively attenuating information across distant spatial positions and weakening global consistency. Together, these effects limit the effectiveness of state-space modelling in high-fidelity restoration. We propose Progressive Split-Mamba (PS-Mamba), a topology-aware hierarchical state-space framework designed to reconcile locality preservation with efficient global propagation. Instead of sequentially flattening entire feature maps, PS-Mamba performs geometry-consistent partitioning, maintaining neighbourhood integrity prior to state-space processing. A progressive split hierarchy (halves, quadrants, octants) enables structured multi-scale modelling while retaining linear complexity. To counteract long-range decay, we introduce symmetric cross-scale shortcut pathways that directly transmit low-frequency global context across hierarchical levels, stabilising information flow over large spatial extents. Extensive experiments on super-resolution, denoising, and JPEG artifact reduction show consistent improvements over recent Mamba-based and attention-based models with a clear margin.

cs.CV↗

arXiv2026

Collaborative Zone-Adaptive Zero-Day Intrusion Detection for IoBT

The Internet of Battlefield Things (IoBT) relies on heterogeneous, bandwidth-constrained, and intermittently connected tactical networks that face rapidly evolving cyber threats. In this setting, intrusion detection cannot depend on continuous central collection of raw traffic due to disrupted links, latency, operational security limits, and non-IID traffic across zones. We present Zone-Adaptive Intrusion Detection (ZAID), a collaborative detection and model-improvement framework for unseen attack types, where "zero-day" refers to previously unobserved attack families and behaviours (not vulnerability disclosure timing). ZAID combines a universal convolutional model for generalisable traffic representations, an autoencoder-based reconstruction signal as an auxiliary anomaly score, and lightweight adapter modules for parameter-efficient zone adaptation. To support cross-zone generalisation under constrained connectivity, ZAID uses federated aggregation and pseudo-labelling to leverage locally observed, weakly labelled behaviours. We evaluate ZAID on ToN_IoT using a zero-day protocol that excludes MITM, DDoS, and DoS from supervised training and introduces them during zone-level deployment and adaptation. ZAID achieves up to 83.16% accuracy on unseen attack traffic and transfers to UNSW-NB15 under the same procedure, with a best accuracy of 71.64%. These results indicate that parameter-efficient, zone-personalised collaboration can improve the detection of previously unseen attacks in contested IoBT environments.

cs.CR↗

arXiv2025

DEFENDCLI: {Command-Line} Driven Attack Provenance Examination

Endpoint Detection and Response (EDR) solutions embrace the method of attack provenance graph to discover unknown threats through system event correlation. However, this method still faces some unsolved problems in the fields of interoperability, reliability, flexibility, and practicability to deliver actionable results. Our research highlights the limitations of current solutions in detecting obfuscation, correlating attacks, identifying low-frequency events, and ensuring robust context awareness in relation to command-line activities. To address these challenges, we introduce DEFENDCLI, an innovative system leveraging provenance graphs that, for the first time, delves into command-line-level detection. By offering finer detection granularity, it addresses a gap in modern EDR systems that has been overlooked in previous research. Our solution improves the precision of the information representation by evaluating differentiation across three levels: unusual system process calls, suspicious command-line executions, and infrequent external network connections. This multi-level approach enables EDR systems to be more reliable in complex and dynamic environments. Our evaluation demonstrates that DEFENDCLI improves precision by approximately 1.6x compared to the state-of-the-art methods on the DARPA Engagement Series attack datasets. Extensive real-time industrial testing across various attack scenarios further validates its practical effectiveness. The results indicate that DEFENDCLI not only detects previously unknown attack instances, which are missed by other modern commercial solutions, but also achieves a 2.3x improvement in precision over the state-of-the-art research work.

cs.CR↗

arXiv2025

Temporal Analysis of NetFlow Datasets for Network Intrusion Detection Systems

This paper investigates the temporal analysis of NetFlow datasets for machine learning (ML)-based network intrusion detection systems (NIDS). Although many previous studies have highlighted the critical role of temporal features, such as inter-packet arrival time and flow length/duration, in NIDS, the currently available NetFlow datasets for NIDS lack these temporal features. This study addresses this gap by creating and making publicly available a set of NetFlow datasets that incorporate these temporal features [1]. With these temporal features, we provide a comprehensive temporal analysis of NetFlow datasets by examining the distribution of various features over time and presenting time-series representations of NetFlow features. This temporal analysis has not been previously provided in the existing literature. We also borrowed an idea from signal processing, time frequency analysis, and tested it to see how different the time frequency signal presentations (TFSPs) are for various attacks. The results indicate that many attacks have unique patterns, which could help ML models to identify them more easily.

cs.LG↗

arXiv2024

A Comprehensive Overview of Large Language Models (LLMs) for Cyber Defences: Opportunities and Directions

The recent progression of Large Language Models (LLMs) has witnessed great success in the fields of data-centric applications. LLMs trained on massive textual datasets showed ability to encode not only context but also ability to provide powerful comprehension to downstream tasks. Interestingly, Generative Pre-trained Transformers utilised this ability to bring AI a step closer to human being replacement in at least datacentric applications. Such power can be leveraged to identify anomalies of cyber threats, enhance incident response, and automate routine security operations. We provide an overview for the recent activities of LLMs in cyber defence sections, as well as categorization for the cyber defence sections such as threat intelligence, vulnerability assessment, network security, privacy preserving, awareness and training, automation, and ethical guidelines. Fundamental concepts of the progression of LLMs from Transformers, Pre-trained Transformers, and GPT is presented. Next, the recent works of each section is surveyed with the related strengths and weaknesses. A special section about the challenges and directions of LLMs in cyber security is provided. Finally, possible future research directions for benefiting from LLMs in cyber security is discussed.

cs.CR↗

arXiv2022

Feature Extraction for Machine Learning-based Intrusion Detection in IoT Networks

A large number of network security breaches in IoT networks have demonstrated the unreliability of current Network Intrusion Detection Systems (NIDSs). Consequently, network interruptions and loss of sensitive data have occurred, which led to an active research area for improving NIDS technologies. In an analysis of related works, it was observed that most researchers aim to obtain better classification results by using a set of untried combinations of Feature Reduction (FR) and Machine Learning (ML) techniques on NIDS datasets. However, these datasets are different in feature sets, attack types, and network design. Therefore, this paper aims to discover whether these techniques can be generalised across various datasets. Six ML models are utilised: a Deep Feed Forward (DFF), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Decision Tree (DT), Logistic Regression (LR), and Naive Bayes (NB). The accuracy of three Feature Extraction (FE) algorithms; Principal Component Analysis (PCA), Auto-encoder (AE), and Linear Discriminant Analysis (LDA), are evaluated using three benchmark datasets: UNSW-NB15, ToN-IoT and CSE-CIC-IDS2018. Although PCA and AE algorithms have been widely used, the determination of their optimal number of extracted dimensions has been overlooked. The results indicate that no clear FE method or ML model can achieve the best scores for all datasets. The optimal number of extracted dimensions has been identified for each dataset, and LDA degrades the performance of the ML models on two datasets. The variance is used to analyse the extracted dimensions of LDA and PCA. Finally, this paper concludes that the choice of datasets significantly alters the performance of the applied techniques. We believe that a universal (benchmark) feature set is needed to facilitate further advancement and progress of research in this field.

cs.NI↗

arXiv2021

A Cyber Threat Intelligence Sharing Scheme based on Federated Learning for Network Intrusion Detection

The uses of Machine Learning (ML) in detection of network attacks have been effective when designed and evaluated in a single organisation. However, it has been very challenging to design an ML-based detection system by utilising heterogeneous network data samples originating from several sources. This is mainly due to privacy concerns and the lack of a universal format of datasets. In this paper, we propose a collaborative federated learning scheme to address these issues. The proposed framework allows multiple organisations to join forces in the design, training, and evaluation of a robust ML-based network intrusion detection system. The threat intelligence scheme utilises two critical aspects for its application; the availability of network data traffic in a common format to allow for the extraction of meaningful patterns across data sources. Secondly, the adoption of a federated learning mechanism to avoid the necessity of sharing sensitive users' information between organisations. As a result, each organisation benefits from other organisations cyber threat intelligence while maintaining the privacy of its data internally. The model is trained locally and only the updated weights are shared with the remaining participants in the federated averaging process. The framework has been designed and evaluated in this paper by using two key datasets in a NetFlow format known as NF-UNSW-NB15-v2 and NF-BoT-IoT-v2. Two other common scenarios are considered in the evaluation process; a centralised training method where the local data samples are shared with other organisations and a localised training method where no threat intelligence is shared. The results demonstrate the efficiency and effectiveness of the proposed framework by designing a universal ML model effectively classifying benign and intrusive traffic originating from multiple organisations without the need for local data exchange.

cs.LG↗

arXiv2021

A Deep Learning-based Penetration Testing Framework for Vulnerability Identification in Internet of Things Environments

The Internet of Things (IoT) paradigm has displayed tremendous growth in recent years, resulting in innovations like Industry 4.0 and smart environments that provide improvements to efficiency, management of assets and facilitate intelligent decision making. However, these benefits are offset by considerable cybersecurity concerns that arise due to inherent vulnerabilities, which hinder IoT-based systems' Confidentiality, Integrity, and Availability. Security vulnerabilities can be detected through the application of penetration testing, and specifically, a subset of the information-gathering stage, known as vulnerability identification. Yet, existing penetration testing solutions can not discover zero-day vulnerabilities from IoT environments, due to the diversity of generated data, hardware constraints, and environmental complexity. Thus, it is imperative to develop effective penetration testing solutions for the detection of vulnerabilities in smart IoT environments. In this paper, we propose a deep learning-based penetration testing framework, namely Long Short-Term Memory Recurrent Neural Network-Enabled Vulnerability Identification (LSTM-EVI). We utilize this framework through a novel cybersecurity-oriented testbed, which is a smart airport-based testbed comprised of both physical and virtual elements. The framework was evaluated using this testbed and on real-time data sources. Our results revealed that the proposed framework achieves about 99% detection accuracy for scanning attacks, outperforming other four peer techniques.

cs.CR↗

arXiv2021

Hunter in the Dark: Discover Anomalous Network Activity Using Deep Ensemble Network

Machine learning (ML)-based intrusion detection systems (IDSs) play a critical role in discovering unknown threats in a large-scale cyberspace. They have been adopted as a mainstream hunting method in many organizations, such as financial institutes, manufacturing companies and government agencies. However, existing designs achieve a high threat detection performance at the cost of a large number of false alarms, leading to alert fatigue. To tackle this issue, in this paper, we propose a neural-network-based defense mechanism named DarkHunter. DarkHunter incorporates both supervised learning and unsupervised learning in the design. It uses a deep ensemble network (trained through supervised learning) to detect anomalous network activities and exploits an unsupervised learning-based scheme to trim off mis-detection results. For each detected threat, DarkHunter can trace to its source and present the threat in its original traffic format. Our evaluations, based on the UNSW-NB15 dataset, show that DarkHunter outperforms the existing ML-based IDSs and is able to achieve a high detection accuracy while keeping a low false positive rate.

cs.CR↗

arXiv2021

Security and Privacy for Artificial Intelligence: Opportunities and Challenges

The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models are vulnerable to advanced and sophisticated hacking techniques. This challenge has motivated concerted research efforts into adversarial AI, with the aim of developing robust machine and deep learning models that are resilient to different types of adversarial scenarios. In this paper, we present a holistic cyber security review that demonstrates adversarial attacks against AI applications, including aspects such as adversarial knowledge and capabilities, as well as existing methods for generating adversarial examples and existing cyber defence models. We explain mathematical AI models, especially new variants of reinforcement and federated learning, to demonstrate how attack vectors would exploit vulnerabilities of AI models. We also propose a systematic framework for demonstrating attack techniques against AI applications and reviewed several cyber defences that would protect AI applications against those attacks. We also highlight the importance of understanding the adversarial goals and their capabilities, especially the recent attacks against industry applications, to develop adaptive defences that assess to secure AI applications. Finally, we describe the main challenges and future research directions in the domain of security and privacy of AI technologies.

cs.CR↗

arXiv2020

A Deep Marginal-Contrastive Defense against Adversarial Attacks on 1D Models

Deep learning algorithms have been recently targeted by attackers due to their vulnerability. Several research studies have been conducted to address this issue and build more robust deep learning models. Non-continuous deep models are still not robust against adversarial, where most of the recent studies have focused on developing attack techniques to evade the learning process of the models. One of the main reasons behind the vulnerability of such models is that a learning classifier is unable to slightly predict perturbed samples. To address this issue, we propose a novel objective/loss function, the so-called marginal contrastive, which enforces the features to lie under a specified margin to facilitate their prediction using deep convolutional networks (i.e., Char-CNN). Extensive experiments have been conducted on continuous cases (e.g., UNSW NB15 dataset) and discrete ones (i.e, eight-large-scale datasets [32]) to prove the effectiveness of the proposed method. The results revealed that the regularization of the learning process based on the proposed loss function can improve the performance of Char-CNN.

cs.CR↗

arXiv2020

Mitigating the Impact of Adversarial Attacks in Very Deep Networks

Deep Neural Network (DNN) models have vulnerabilities related to security concerns, with attackers usually employing complex hacking techniques to expose their structures. Data poisoning-enabled perturbation attacks are complex adversarial ones that inject false data into models. They negatively impact the learning process, with no benefit to deeper networks, as they degrade a model's accuracy and convergence rates. In this paper, we propose an attack-agnostic-based defense method for mitigating their influence. In it, a Defensive Feature Layer (DFL) is integrated with a well-known DNN architecture which assists in neutralizing the effects of illegitimate perturbation samples in the feature space. To boost the robustness and trustworthiness of this method for correctly classifying attacked input samples, we regularize the hidden space of a trained model with a discriminative loss function called Polarized Contrastive Loss (PCL). It improves discrimination among samples in different classes and maintains the resemblance of those in the same class. Also, we integrate a DFL and PCL in a compact model for defending against data poisoning attacks. This method is trained and tested using the CIFAR-10 and MNIST datasets with data poisoning-enabled perturbation attacks, with the experimental results revealing its excellent performance compared with those of recent peer techniques.

cs.CV↗

arXiv2020

NetFlow Datasets for Machine Learning-based Network Intrusion Detection Systems

Machine Learning (ML)-based Network Intrusion Detection Systems (NIDSs) have proven to become a reliable intelligence tool to protect networks against cyberattacks. Network data features has a great impact on the performances of ML-based NIDSs. However, evaluating ML models often are not reliable, as each ML-enabled NIDS is trained and validated using different data features that may do not contain security events. Therefore, a common ground feature set from multiple datasets is required to evaluate an ML model's detection accuracy and its ability to generalise across datasets. This paper presents NetFlow features from four benchmark NIDS datasets known as UNSW-NB15, BoT-IoT, ToN-IoT, and CSE-CIC-IDS2018 using their publicly available packet capture files. In a real-world scenario, NetFlow features are relatively easier to extract from network traffic compared to the complex features used in the original datasets, as they are usually extracted from packet headers. The generated Netflow datasets have been labelled for solving binary- and multiclass-based learning challenges. Preliminary results indicate that NetFlow features lead to similar binary-class results and lower multi-class classification results amongst the four datasets compared to their respective original features datasets. The NetFlow datasets are named NF-UNSW-NB15, NF-BoT-IoT, NF-ToN-IoT, NF-CSE-CIC-IDS2018 and NF-UQ-NIDS are published at http://staff.itee.uq.edu.au/marius/NIDS_datasets/ for research purposes.

cs.NI↗

arXiv2020

Data Analytics-enabled Intrusion Detection: Evaluations of ToN_IoT Linux Datasets

With the widespread of Artificial Intelligence (AI)- enabled security applications, there is a need for collecting heterogeneous and scalable data sources for effectively evaluating the performances of security applications. This paper presents the description of new datasets, named ToN IoT datasets that include distributed data sources collected from Telemetry datasets of Internet of Things (IoT) services, Operating systems datasets of Windows and Linux, and datasets of Network traffic. The paper aims to describe the new testbed architecture used to collect Linux datasets from audit traces of hard disk, memory and process. The architecture was designed in three distributed layers of edge, fog, and cloud. The edge layer comprises IoT and network systems, the fog layer includes virtual machines and gateways, and the cloud layer includes data analytics and visualization tools connected with the other two layers. The layers were programmatically controlled using Software-Defined Network (SDN) and Network-Function Virtualization (NFV) using the VMware NSX and vCloud NFV platform. The Linux ToN IoT datasets would be used to train and validate various new federated and distributed AI-enabled security solutions such as intrusion detection, threat intelligence, privacy preservation and digital forensics. Various Data analytical and machine learning methods are employed to determine the fidelity of the datasets in terms of examining feature engineering, statistics of legitimate and security events, and reliability of security events. The datasets can be publicly accessed from [1].

cs.CR↗

arXiv2020

Federated TON_IoT Windows Datasets for Evaluating AI-based Security Applications

Existing cyber security solutions have been basically developed using knowledge-based models that often cannot trigger new cyber-attack families. With the boom of Artificial Intelligence (AI), especially Deep Learning (DL) algorithms, those security solutions have been plugged-in with AI models to discover, trace, mitigate or respond to incidents of new security events. The algorithms demand a large number of heterogeneous data sources to train and validate new security systems. This paper presents the description of new datasets, the so-called ToN_IoT, which involve federated data sources collected from telemetry datasets of IoT services, operating system datasets of Windows and Linux, and datasets of network traffic. The paper introduces the testbed and description of TON_IoT datasets for Windows operating systems. The testbed was implemented in three layers: edge, fog and cloud. The edge layer involves IoT and network devices, the fog layer contains virtual machines and gateways, and the cloud layer involves cloud services, such as data analytics, linked to the other two layers. These layers were dynamically managed using the platforms of software-Defined Network (SDN) and Network-Function Virtualization (NFV) using the VMware NSX and vCloud NFV platform. The Windows datasets were collected from audit traces of memories, processors, networks, processes and hard disks. The datasets would be used to evaluate various AI-based cyber security solutions, including intrusion detection, threat intelligence and hunting, privacy preservation and digital forensics. This is because the datasets have a wide range of recent normal and attack features and observations, as well as authentic ground truth events. The datasets can be publicly accessed from this link [1].

cs.CR↗

arXiv2020

Densely Connected Residual Network for Attack Recognition

High false alarm rate and low detection rate are the major sticking points for unknown threat perception. To address the problems, in the paper, we present a densely connected residual network (Densely-ResNet) for attack recognition. Densely-ResNet is built with several basic residual units, where each of them consists of a series of Conv-GRU subnets by wide connections. Our evaluation shows that Densely-ResNet can accurately discover various unknown threats that appear in edge, fog and cloud layers and simultaneously maintain a much lower false alarm rate than existing algorithms.

cs.CR↗

arXiv2020

Pelican: A Deep Residual Network for Network Intrusion Detection

One challenge for building a secure network communication environment is how to effectively detect and prevent malicious network behaviours. The abnormal network activities threaten users' privacy and potentially damage the function and infrastructure of the whole network. To address this problem, the network intrusion detection system (NIDS) has been used. By continuously monitoring network activities, the system can timely identify attacks and prompt counter-attack actions. NIDS has been evolving over years. The current-generation NIDS incorporates machine learning (ML) as the core technology in order to improve the detection performance on novel attacks. However, the high detection rate achieved by a traditional ML-based detection method is often accompanied by large false-alarms, which greatly affects its overall performance. In this paper, we propose a deep neural network, Pelican, that is built upon specially-designed residual blocks. We evaluated Pelican on two network traffic datasets, NSL-KDD and UNSW-NB15. Our experiments show that Pelican can achieve a high attack detection performance while keeping a much low false alarm rate when compared with a set of up-to-date machine learning based designs.

cs.LG↗

arXiv2020

Enhancing network forensics with particle swarm and deep learning: The particle deep framework

The popularity of IoT smart things is rising, due to the automation they provide and its effects on productivity. However, it has been proven that IoT devices are vulnerable to both well established and new IoT-specific attack vectors. In this paper, we propose the Particle Deep Framework, a new network forensic framework for IoT networks that utilised Particle Swarm Optimisation to tune the hyperparameters of a deep MLP model and improve its performance. The PDF is trained and validated using Bot-IoT dataset, a contemporary network-traffic dataset that combines normal IoT and non-IoT traffic, with well known botnet-related attacks. Through experimentation, we show that the performance of a deep MLP model is vastly improved, achieving an accuracy of 99.9% and false alarm rate of close to 0%.

cs.CR↗