Rafiqul Islam

Sk. Tanzir Mehedi, Adnan Anwar, Ziaur Rahman et al.

Security concerns for IoT applications have been alarming because of their widespread use in different enterprise systems. The potential threats to these applications are constantly emerging and changing, and therefore, sophisticated and dependable defense solutions are necessary against such threats. With the rapid development of IoT networks and evolving threat types, the traditional machine learning-based IDS must update to cope with the security requirements of the current sustainable IoT environment. In recent years, deep learning, and deep transfer learning have progressed and experienced great success in different fields and have emerged as a potential solution for dependable network intrusion detection. However, new and emerging challenges have arisen related to the accuracy, efficiency, scalability, and dependability of the traditional IDS in a heterogeneous IoT setup. This manuscript proposes a deep transfer learning-based dependable IDS model that outperforms several existing approaches. The unique contributions include effective attribute selection, which is best suited to identify normal and attack scenarios for a small amount of labeled data, designing a dependable deep transfer learning-based ResNet model, and evaluating considering real-world data. To this end, a comprehensive experimental performance evaluation has been conducted. Extensive analysis and performance evaluation show that the proposed model is robust, more efficient, and has demonstrated better performance, ensuring dependability.

Mustain Billah, Sk. Tanzir Mehedi, Adnan Anwar et al.

While the convergence of Artificial Intelligence (AI) techniques with improved information technology systems ensured enormous benefits to the Internet of Vehicles (IoVs) systems, it also introduced an increased amount of security and privacy threats. To ensure the security of IoVs data, privacy preservation methodologies have gained significant attention in the literature. However, these strategies also need specific adjustments and modifications to cope with the advances in IoVs design. In the interim, Federated Learning (FL) has been proven as an emerging idea to protect IoVs data privacy and security. On the other hand, Blockchain technology is showing prominent possibilities with secured, dispersed, and auditable data recording and sharing schemes. In this paper, we present a comprehensive survey on the application and implementation of Blockchain-Enabled Federated Learning frameworks for IoVs. Besides, probable issues, challenges, solutions, and future research directions for BC-Enabled FL frameworks for IoVs are also presented. This survey can further be used as the basis for developing modern BC-Enabled FL solutions to resolve different data privacy issues and scenarios of IoVs.

Md Mehedi Hasan, Rafiqul Islam, Md Zakir Hossain

False data injection (FDI) attacks on Internet of Medical Things (IoMT) sensor streams falsify vital signs in transit, threatening patient safety and defeating clinical monitoring systems that lack cyber-physical anomaly detection capability. Existing deep learning detectors conflate inter-sensor spatial correlations with temporal dependencies in a shared latent space, preventing disentanglement of the distinct spatial and temporal signatures that FDI attacks imprint simultaneously; no current method exploits domain knowledge to constrain outputs against physiologically impossible attack patterns. We propose DSTAN-Med, a supervised framework comprising a Dual-channel Attention Mechanism (DAM) that routes multivariate sensor windows through independent sensor-wise (SWA) and time-wise (TWA) self-attention pathways operating on orthogonal tensor axes, a residual 1D-CNN block for local temporal feature extraction, and a zero-parameter Physiological Plausibility Filter (PPF) that suppresses attack signatures violating domain-knowledge bounds. Evaluated across three IoMT sensor datasets - PhysioNet/CinC 2012 (ICU vital signs), MIMIC-III Waveform (continuous ICU waveforms), and WESAD (wearable biosensor signals) - DSTAN-Med achieves mean sensitivity gains of 7.4-8.3 percentage points over the strongest Transformer baseline (TranAD), with improvements significant at p < 0.01 (McNemar's test, Holm-Bonferroni correction). The PPF contributes independent precision gains of 3.1-4.2 percentage points at negligible sensitivity cost across all three corpora. Ablation studies confirm that each component is individually necessary; removal of residual connections alone reduces sensitivity by 14.0 percentage points. The source code is publicly available at https://github.com/mehedi93hasan/DSTAN-MED.

Jannatul Ferdous, Rafiqul Islam, Arash Mahboubi et al.

Modern ransomware exhibits polymorphic and evasive behaviors by frequently modifying execution patterns to evade detection. This dynamic nature disrupts feature spaces and limits the effectiveness of static or predefined models. To address this challenge, we propose TL-RL-FusionNet, a reinforcement learning (RL)-guided hybrid framework that integrates frozen dual transfer learning (TL) backbones as feature extractors with a lightweight residual multilayer perceptron (MLP) classifier. The RL agent supervises training by adaptively reweighting samples in response to variations in observable ransomware behavior. Through reward and penalty signals, the agent prioritizes complex cases such as stealthy or polymorphic ransomware employing obfuscation, while down-weighting trivial samples including benign applications with simple file I/O operations or easily classified ransomware. This adaptive mechanism enables the model to dynamically refine its strategy, improving resilience against evolving threats while maintaining strong classification performance. The framework utilizes dynamic behavioral features such as file system activity, registry changes, network traffic, API calls, and anti-analysis checks, extracted from sandbox-generated JSON reports. These features are transformed into RGB images and processed using frozen EfficientNetB0 and InceptionV3 models to capture rich feature representations efficiently. Final classification is performed by a lightweight residual MLP guided by an RL (Q-learning) agent. Experiments on a balanced dataset of 1,000 samples (500 ransomware, 500 benign) show that TL-RL-FusionNet achieves 99.1% accuracy, 98.6% precision, 99.6% recall, and 99.74% AUC, outperforming non-RL baselines by up to 2.5% in accuracy and 3.1% in recall. Efficiency analysis shows 55% lower training time and 59% reduced RAM usage, demonstrating suitability for real-world deployment.

Jannatul Ferdous, Rafiqul Islam, Md Zahidul Islam

Ransomware detection systems increasingly rely on behavior-based machine learning to address evolving attack strategies. However, emerging privacy compliance, data governance, and responsible AI deployment demand not only accurate detection but also the ability to efficiently remove the influence of specific training samples without retraining the models from scratch. In this study, we present a privacy-aware machine unlearning evaluation framework for reinforcement learning (RL)-based ransomware detection built on Sharded, Isolated, Sliced, and Aggregated (SISA) training. The framework enables efficient data deletion by retraining only the affected model shards rather than the entire detector, reducing the retraining cost while preserving detection performance. We conduct a controlled comparative study using value-based RL agents, including Deep Q-Network (DQN) and Double Deep Q-Network (DDQN), under identical experimental settings with a cost-sensitive reward design and 5-fold cross-validation on Windows 11 ransomware dataset. Detection confidence is evaluated using a continuous Q-score margin, enabling ROC-AUC analysis beyond binary predictions. For unlearning, the dataset is partitioned into five shards with majority-vote aggregation, and a fast-unlearning path is evaluated by deleting 5% of the samples from a single shard and retraining only that shard. Results show that SISA-based unlearning incurs negligible utility degradation (<= 0.05 percent F1 drop) while substantially reducing retraining time relative to full SISA retraining. DDQN exhibits slightly improved stability and lower utility loss than DQN, while both agents maintain near identical in-distribution performance after unlearning. These findings indicate that SISA provides an efficient unlearning mechanism for RL-based ransomware detection, supporting privacy-aware deployment without compromising security effectiveness.

N. I. Md. Ashafuddula, Rafiqul Islam

Melanoma skin cancer is one of the most dangerous and life-threatening cancer. Exposure to ultraviolet rays may damage the skin cell's DNA, which causes melanoma skin cancer. However, it is difficult to detect and classify melanoma and nevus mole at the immature stages. In this work, an automatic deep learning system is developed based on the intensity value estimation with a convolutional neural network model (CNN) to detect and classify melanoma and nevus mole more accurately. Since intensity levels are the most distinctive features for object or region of interest identification, the high-intensity pixel values are selected from the extracted lesion images. Incorporating those high-intensity features into the CNN improves the overall performance of the proposed model than the state-of-the-art methods for detecting melanoma skin cancer. To evaluate the system, we used 5-fold cross-validation. Experimental results show that a superior percentage of accuracy (92.58%), sensitivity (93.76%), specificity (91.56%), and precision (90.68%) are achieved.

Jamil Ispahany, Rafiqul Islam

Throughout the COVID-19 outbreak, malicious attacks have become more pervasive and damaging than ever. Malicious intruders have been responsible for most cybercrimes committed recently and are the cause for a growing number of cyber threats, including identity and IP thefts, financial crimes, and cyber-attacks to critical infrastructures. Machine learning (ML) has proven itself as a prominent field of study over the past decade by solving many highly complex and sophisticated real-world problems. This paper proposes an ML-based classification technique to detect the growing number of malicious URLs, due to the COVID-19 pandemic, which is currently considered a threat to IT users. We have used a large volume of Open Source data and preprocessed it using our developed tool to generate feature vectors and we trained the ML model using the apprehensive malicious threat weight. Our ML model has been tested, with and without entropy to forecast the threatening factors of COVID-19 URLs. The empirical evidence proves our methods to be a promising mechanism to mitigate COVID-19 related threats early in the attack lifecycle.

Muhammad Riaz Hasib Hossain, Rafiqul Islam, Shawn R. McGrath et al.

Many cattle farmers still depend on manual methods to measure the live weight gain of cattle at set intervals, which is time consuming, labour intensive, and stressful for both the animals and handlers. A remote and autonomous monitoring system using machine learning (ML) or deep learning (DL) can provide a more efficient and less invasive method and also predictive capabilities for future cattle weight gain (CWG). This system allows continuous monitoring and estimation of individual cattle live weight gain, growth rates and weight fluctuations considering various factors like environmental conditions, genetic predispositions, feed availability, movement patterns and behaviour. Several researchers have explored the efficiency of estimating CWG using ML and DL algorithms. However, estimating CWG suffers from a lack of consistency in its application. Moreover, ML or DL can provide weight gain estimations based on several features that vary in existing research. Additionally, previous studies have encountered various data related challenges when estimating CWG. This paper presents a comprehensive investigation in estimating CWG using advanced ML techniques based on research articles (between 2004 and 2024). This study investigates the current tools, methods, and features used in CWG estimation, as well as their strengths and weaknesses. The findings highlight the significance of using advanced ML approaches in CWG estimation and its critical influence on factors. Furthermore, this study identifies potential research gaps and provides research direction on CWG prediction, which serves as a reference for future research in this area.

Nazatul Haque Sultan, Yan Bo, Yansong Gao et al.

Federated Learning (FL) enables multiple users to collaboratively train a machine learning model without sharing raw data, making it suitable for privacy-sensitive applications. However, local model or weight updates can still leak sensitive information. Secure aggregation protocols mitigate this risk by ensuring that only the aggregated updates are revealed. Among these, single-setup protocols, where key generation and exchange occur only once, are the most efficient due to reduced communication and computation overhead. However, existing single-setup protocols often lack support for dynamic user participation and do not provide strong privacy guarantees such as forward and backward secrecy. \par In this paper, we present a novel secure aggregation protocol that requires only a single setup for the entire FL training. Our protocol supports dynamic user participation, tolerates dropouts, and achieves both forward and backward secrecy. It leverages lightweight symmetric homomorphic encryption with a key negation technique to mask updates efficiently, eliminating the need for user-to-user communication. To defend against model inconsistency attacks, we introduce a low-overhead verification mechanism using message authentication codes (MACs). We provide formal security proofs under both semi-honest and malicious adversarial models and implement a full prototype. Experimental results show that our protocol reduces user-side computation by up to $99\%$ compared to state-of-the-art protocols like e-SeaFL (ACSAC'24), while maintaining competitive model accuracy. These features make our protocol highly practical for real-world FL deployments, especially on resource-constrained devices.

Muhammad Riaz Hasib Hossain, Rafiqul Islam, Shawn R McGrath et al.

Forecasting mob based cattle weight gain (MB CWG) may benefit large livestock farms, allowing farmers to refine their feeding strategies, make educated breeding choices, and reduce risks linked to climate variability and market fluctuations. In this paper, a novel technique termed MB CWG is proposed to forecast the one month advanced weight gain of herd based cattle using historical data collected from the Charles Sturt University Farm. This research employs a Random Forest (RF) model, comparing its performance against Support Vector Regression (SVR) and Long Short Term Memory (LSTM) models for monthly weight gain prediction. Four datasets were used to evaluate the performance of models, using 756 sample data from 108 herd-based cattle, along with weather data (rainfall and temperature) influencing CWG. The RF model performs better than the SVR and LSTM models across all datasets, achieving an R^2 of 0.973, RMSE of 0.040, and MAE of 0.033 when both weather and age factors were included. The results indicate that including both weather and age factors significantly improves the accuracy of weight gain predictions, with the RF model outperforming the SVR and LSTM models in all scenarios. These findings demonstrate the potential of RF as a robust tool for forecasting cattle weight gain in variable conditions, highlighting the influence of age and climatic factors on herd based weight trends. This study has also developed an innovative automated pre processing tool to generate a benchmark dataset for MB CWG predictive models. The tool is publicly available on GitHub and can assist in preparing datasets for current and future analytical research..

Muhammad Rana, Quazi Mamun, Rafiqul Islam

With the advent of advanced technology, IoT introduces a vast number of devices connecting with each other and collecting a sheer volume of data. Thus, the demands of IoT security is paramount. Cryptography is being used to secure the networks for authentication, confidentiality, data integrity and access control. However, due to the resource constraint nature of IoT devices, the traditional cryptographic protocols may not be suited in all IoT environments. Researchers, as a result, have been proposing various lightweight cryptographic algorithms and protocols. In this paper, we discuss the state of the art lightweight cryptographic protocols for IoT networks and present a comparative analysis of the existing protocols. In doing so, this paper has classified the most current algorithm into two parts, such as symmetric and asymmetric lightweight cryptography. Additionally, we consider several recent developed block cipher and stream cipher algorithms. Furthermore, various research challenges of lightweight cryptography have been addressed.

Ishan Karunanayake, Nadeem Ahmed, Robert Malaney et al.

Anonymity networks are becoming increasingly popular in today's online world as more users attempt to safeguard their online privacy. Tor is currently the most popular anonymity network in use and provides anonymity to both users and services (hidden services). However, the anonymity provided by Tor is also being misused in various ways. Hosting illegal sites for selling drugs, hosting command and control servers for botnets, and distributing censored content are but a few such examples. As a result, various parties, including governments and law enforcement agencies, are interested in attacks that assist in de-anonymising the Tor network, disrupting its operations, and bypassing its censorship circumvention mechanisms. In this survey paper, we review known Tor attacks and identify current techniques for the de-anonymisation of Tor users and hidden services. We discuss these techniques and analyse the practicality of their execution method. We conclude by discussing improvements to the Tor framework that help prevent the surveyed de-anonymisation attacks.

Mithun Biswas, Rafiqul Islam, Gautam Kumar Shom et al.

Bangla handwriting recognition is becoming a very important issue nowadays. It is potentially a very important task specially for Bangla speaking population of Bangladesh and West Bengal. By keeping that in our mind we are introducing a comprehensive Bangla handwritten character dataset named BanglaLekha-Isolated. This dataset contains Bangla handwritten numerals, basic characters and compound characters. This dataset was collected from multiple geographical location within Bangladesh and includes sample collected from a variety of aged groups. This dataset can also be used for other classification problems i.e: gender, age, district. This is the largest dataset on Bangla handwritten characters yet.

Rafiqul Islam, Iftekharul Mobin, Md. Nazmus Shakib et al.

This paper exhibits a short-run correspondence method appropriate for swarm versatile robots application. Infrared is utilized for transmitting and accepting information and obstruction location. The infrared correspondence code based swarm signaling is utilized for an independent versatile robot communication system in this research. A code based signaling system is developed for transmitting information between different entities of robot. The reflected infrared sign is additionally utilized for separation estimation for obstruction evasion. Investigation of robot demonstrates the possibility of utilizing infrared signs to get a solid nearby correspondence between swarm portable robots. This paper exhibits a basic decentralized control for swarm of self-collecting robots. Every robot in the code based swarm signaling is completely self-governing and controlled utilizing a conduct based methodology with just infrared-based nearby detecting and correspondences. The viability of the methodology has been checked with simulation, for a set of swarm robots.