Through NCS’s journal-first initiative, authors of journal-first papers accepted in the following journals are invited to present their research work to the wider audiences. It is providing an opportunity for the authors to engage directly with the conference authors and offering an additional dimension to the research track program.
The journal-first manuscripts will not be part of the NCS conference proceedings.
Sudhanshu Sekhar Tripathy and Bichitrananda Behera, C.V. Raman Global University, India
Network Intrusion Detection Systems (NIDS) are essential for securing networks by identifying and mitigating unauthorized activities indicative of cyberattacks. As cyber threats grow increasingly sophisticated, NIDS must evolve to detect both emerging threats and deviations from normal behavior. This study explores the application of machine learning (ML) methods to improve the NIDS accuracy through analyzing intricate structures in deep-featured network traffic records. Leveraging the 1999 KDD CUP intrusion dataset as a benchmark, this research evaluates and optimizes several ML algorithms, including Support Vector Machines (SVM), Naïve Bayes variants (MNB, BNB), Random Forest (RF), k-Nearest Neighbors (k-NN), Decision Trees (DT), AdaBoost, XGBoost, Logistic Regression (LR), Ridge Classifier, Passive-Aggressive (PA) Classifier, Rocchio Classifier, Artificial Neural Networks (ANN), and Perceptron (PPN). Initial evaluations without hyper-parameter optimization demonstrated suboptimal performance, highlighting the importance of tuning to enhance classification accuracy. After hyper-parameter optimization using grid and random search techniques, the SVM classifier achieved 99.12% accuracy with a 0.0091 False Alarm Rate (FAR), outperforming its default configuration (98.08% accuracy, 0.0123 FAR) and all other classifiers. This result confirms that SVM accomplishes the highest accuracy among the evaluated classifiers. We validated the effectiveness of all classifiers using a tenfold cross-validation approach, incorporating Recursive Feature Elimination (RFE) for feature selection to enhance the classifiers accuracy and efficiency. Our outcomes indicate that ML classifiers are both adaptable and reliable, contributing to enhanced accuracy in systems for detecting network intrusions.
Machine learning classification systems, Network intrusion detection mechanism, KDD CUP 1999 data repository, Hyper-parameter tuning, Performance evaluation, Classification accuracy.
Journal Name: International Journal of Network Security & Its Applications (IJNSA)
Hadeer Alsubaie, Rahaf Althomali and Samah Alajmani, Taif University, Saudi Arabia
Phishing attacks are one of the most aggressive vulnerabilities in cybersecurity networks, typically carried out through social engineering and URL obfuscation. Traditional detection methods struggle to combat advanced techniques applied. In this paper, a deep learning-based approach is proposed to increase the accuracy of phishing detection while reducing the number of false positives. Four models: CNN-BLSTM, SNN, Transformer, and DBN, are developed and evaluated on a phishing dataset that includes critical features such as URL structure, domain age, and presence of HTTPS. The other model, CNN-BLSTM, achieved 98.9% better accuracy, effectively linking URL sequences in space and time. It is found that although deep learning models have a significant improvement over traditional methods in detecting phishing attacks, the level of computational resources still prevents them from real-time applications. Further research includes hybrid models and adversarial approaches to improve state-ofthe-art and practical solutions to address phishing threats. This study highlights a new technological application to Internet security concerns, particularly in the area of combating phishing.
Network Cybersecurity, Phishing Detection, URL, Web security, Deep Learning.
Journal Name: International Journal of Network Security & Its Applications (IJNSA)
Nikitha Merilena Jonnada, University of the Cumberlands, USA
Phishing attacks are one of the most aggressive vulnerabilities in cybersecurity networks, typically carried out through social engineering and URL obfuscation. Traditional detection methods struggle to combat advanced techniques applied. In this paper, a deep learning-based approach is proposed to increase the accuracy of phishing detection while reducing the number of false positives. Four models: CNN-BLSTM, SNN, Transformer, and DBN, are developed and evaluated on a phishing dataset that includes critical features such as URL structure, domain age, and presence of HTTPS. The other model, CNN-BLSTM, achieved 98.9% better accuracy, effectively linking URL sequences in space and time. It is found that although deep learning models have a significant improvement over traditional methods in detecting phishing attacks, the level of computational resources still prevents them from real-time applications. Further research includes hybrid models and adversarial approaches to improve state-ofthe-art and practical solutions to address phishing threats. This study highlights a new technological application to Internet security concerns, particularly in the area of combating phishing.
Network Cybersecurity, Phishing Detection, URL, Web security, Deep Learning.
Journal Name: International Journal of Network Security & Its Applications (IJNSA)
Nikitha Merilena Jonnada, University of the Cumberlands, USA
The author used this paper to discuss the techniques, strategies, and concepts of artificial intelligence and machine learning to learn their uses in providing security and other essential features. The author also discusses the advantages, drawbacks, or limitations of using artificial intelligence and machine learning. Any technology or development comes with certain advantages and limitations. This scenario applies to artificial intelligence and machine learning. By emphasizing the importance of artificial intelligence and machine learning, the author attempts to educate the users and readers about the significant concepts within the study, as this could help many users and organizations to identify the critical factors about these concepts.
Artificial Intelligence, Machine Learning, Virus, Security, Malware, Data.
Journal Name: International Journal of Network Security & Its Applications (IJNSA)
Mahdi Madani a and El-Bay Bourennane, Université Bourgogne Europe, France
This paper proposes a visual encryption method to ensure the confidentiality of digital images. The model used is based on an autoencoder using a Convolutional Neural Network (CNN) to ensure the protection of the user data on both the sender side (encryption process) and the receiver side (decryption process) in a symmetric mode. To train and test the model, we used the MNIST and CIFAR-10 datasets. Our focus lies in generating an encrypted dataset by combining the original dataset with a random mask. Then, a convolutional autoencoder in the masked dataset will be designed and trained to learn essential image features in a reduced-dimensional latent space and reconstruct the image from this space. The used mask can be considered as a secret key known in standard cryptographic algorithms which allows the receiver of the masked data to recover the plain data. The implementation of this proposed encryption model demonstrates efficacy in preserving data confidentiality and integrity while reducing the dimensionality (for example we pass from 3072 Bytes to 1024 Bytes for CIFAR-10 images). Experimental results show that the used CNN exhibits a proficient encryption and decryption process on the MNIST dataset, and a proficient encryption and acceptable decryption process on the CIFAR-10 dataset.
Visually image protection, Masked data, Deep Learning, Encryption and decryption, Autoencoder, Security analysis, Compression.
Journal Name: International Journal of Computer Networks & Communications (IJCNC)
Fei-Hon Kao, Chia-Hsiang Hsieh and Wen Pei, Chung Hua University, Taiwan
This study applies the Consistent Fuzzy Analytic Hierarchy Process (CFAHP) to enhance pre-sales decision-making in the semiconductor industry, addressing its complexity and uncertainty. A hierarchical model was developed with three key dimensions—market, competitive, and technological environments— and nine critical criteria. Based on expert evaluations from eight industry professionals, results indicate that the market environment holds the greatest influence, with customer needs identified as the top priority. Technology trends and risk assessment also emerged as significant factors. The proposed CFAHP model provides a practical and systematic tool to support strategic planning, resource allocation, and risk management in pre-sales processes
Consistent Fuzzy AHP (CFAHP), Pre-sales Strategy, Semiconductor Industry, Multi-Criteria Decision Analysis (MCDA), Customer Needs, Technology Trends
Journal Name: International Journal of Computer Science and Information Technology (IJCSIT)
Abdul Faisal Mohammed 1, Shahnawaz Mohammed 1, Abdul Raheman Mohammed 2 and Syed Abdullah Kamran 1, 1 Trine University, USA, 2 Lindsey Willson College, USA
The construction sector continues to be one of the world's most hazardous, with high rates of accidents fuelled by multicomponent site dynamics, extensive use of heavy equipment, and unstable human behaviour. Conventional safety management methods, although essential, are generally reactive and fall short in offering real-time hazard perception or forecasting risk assessment. Recent advancements in Artificial Intelligence (AI) provide revolutionary opportunities to enhance safety performance through anticipatory, automated, and evidence-based decision-making. This article explains how AI techniques—ranging from computer vision for PPE detection and unsafe behaviour recognition, to wearable sensor analysis for fatigue and stress monitoring, to predictive machine learning models for incident prediction—can significantly enhance construction safety management. Furthermore, the combination of AI with Building Information Modelling (BIM) and digital twin technology allows for real-time hazard mapping, safety scenarios through simulation, and end-to-end synchronization between the virtual and physical worlds. This paper proposes a complete AI-based safety paradigm that harmonizes multimodal data sources, edge analytics, and interpretable predictive models to close the risk mitigation gap with worker privacy and trust. Data quality anomalies, model generalization, alert fatigue, and surveillance implications in terms of ethics are also addressed with responsible deployment practices. AI will eventually be able to shift construction safety from reactive compliance to preventive intervention, reducing incidents and safer conditions.
Artificial Intelligence (AI), Construction Safety, Safety Management, Computer Vision, Wearable Sensors, Predictive Analytics, Digital Twin, Building Information Modelling (BIM), Personal Protective Equipment (PPE), Hazard Prediction, Fatigue Monitoring, Edge Computing, Multimodal Data Fusion, Explainable AI, Risk Mitigation.
Journal Name: International Journal of Computer Science and Information Technology (IJCSIT)
Fatema Tuj Zohra, Rifa Tasfia Ratri, Shaheena Sultana, and Humayara Binte Rashid, Notre Dame University, Bangladesh
Image segmentation and classification tasks in computer vision have proven to be highly effective using neural networks, specifically Convolutional Neural Networks (CNNs). These tasks have numerous practical applications, such as in medical imaging, autonomous driving, and surveillance. CNNs are capable of learning complex features directly from images and achieving outstanding performance across several datasets. In this work, we have utilized three different datasets to investigate the efficacy of various preprocessing and classification techniques in accurssedately segmenting and classifying different structures within the MRI and natural images. We have utilized both sample gradient and Canny Edge Detection methods for pre-processing, and K-means clustering have been applied to segment the images. Image augmentation improves the size and diversity of datasets for training the models for image classification. This work highlights transfer learning’s effectiveness in image classification using CNNs and VGG 16 that provides insights into the selection of pre-trained models and hyper parameters for optimal performance. We have proposed a comprehensive approach for image segmentation and classification, incorporating preprocessing techniques, the K-means algorithm for segmentation, and employing deep learning models such as CNN and VGG 16 for classification.
Convolutional Neural Network, VGG 16, Image Segmentation, K-means, Image Classification.
Journal Name: International Journal of Computer Science and Information Technology (IJCSIT)
Rajkumar M Vadgave, Manjula S and Savitri Kanshete, Bheemanna Khandre Instituteof Technology, India
Designing energy-ef icient WSN is complex. Ef ective routing is crucial for energy ef iciency due to its impact on energy consumption during communication. In WSNs, clustering involves selecting a CH, whichacts as a leader and consumes more energy. This process groups nodes into clusters, minimizing thecommunication range that each CH manages. This paper introduces the Optimized Cluster-Based Energy- Aware Routing (OCEAR) protocol to extend WSN lifetimes. Nodes are organized into clusters based onnode angle and variance, enhancing CH load balancing and distribution. We assess communicationmodels in dif erent scenarios to find those aligning with the free space model, thereby reducing energy usecompared to the multipath fading model. We derive closed-form expressions for the optimal CHnumber and location, linked to network size and energy use, and set an objective function to optimize CHselectionbased on node energy and CH location. OCEAR's energy ef iciency is ideal for battery-dependent devices and resource-limited systems, leading to longer device lifetimes and reduced costs. Compared to LEACH- C, IAFSA, and SCA-LM, OCEAR of ers superior energy ef iciency and network durability.
Wireless Sensor Networks (WSNs); Cluster Head (CH); Base Station (BS); Internet of Things (IoT)
Journal Name: International Journal of Wireless & Mobile Networks (IJWMN)
Dilip Dalgade, NileshPatil, ManujJoshi and Dilendra Hiran, Pacific Academy of Higher Education and Research, India
Wireless Sensor Networks (WSNs) are key for ubiquitous computing. Despite advantages, they face security challenges due to decentralized nature and threats. Intrusion detection helps protect WSNs from security threats. This study proposes an Optuna-implemented stacking technique (OXCRF) the method combines SHapley Additive exPlanations, CatBoost, Mutual Information, and cross-validated Recursive Feature Elimination with Random Forest for feature selection, while SMOTE handles data imbalance. The stacking ensemble, XGBoost, CatBoost and Random Forest are used as the base learners, with hyperparameters being optimized using Optuna. Experiments on the NSL-KDD and UNSW-NB15 datasets show that OXCRF achieves higher accuracy (99.60% for binary and 99.53% for multiclass on NSL-KDD; 98.62% for binary and 83.67% for multiclass on UNSW-NB15) and lower misclassification rates (0.0040 and 0.0047 on NSLKDD; 0.0138 and 0.1633 on UNSW-NB15) compared to baseline models. Running an ablation study showed that OXCRF components worked as expected for multiclass intrusion detection in WSNs with overlapping classes and imbalanced data. The framework is efficient through feature selection, balanced data distribution and improved ensemble learning.
Wireless Sensor Networks, Intrusion Detection, Stacking Ensemble Learning, Optuna, Feature Selection, XGB, CatBoost.
Journal Name: International Journal of Wireless & Mobile Networks (IJWMN)
