Browse Articles
Discover research articles across all indexed journals
A hybrid ensemble deep learning framework with novel metaheuristic optimization for scalable malicious website detection
Abstract The rapid expansion of malicious websites poses a critical threat to online security, as conventional blacklist-based and manual inspection methods cannot keep pace with evolving attacks. In this study, we present a hybrid detection framework that integrates ensemble learning models, Random Forest, Extreme Gradient Boosting, and Light Gradient Boosting with a Deep Neural Network to distinguish malicious from benign websites accurately. The framework leverages a large-scale dataset of 63,191 URLs, combining application-layer attributes (such as URL structure, server type, and WHOIS data) with network-layer features (including TCP exchanges, DNS queries, and packet statistics). Dimensionality reduction is achieved through Principal Component Analysis, while model explainability is provided by SHapley Additive exPlanations. To enhance predictive performance, hyperparameters are tuned using two recent metaheuristic algorithms: the Weevil Damage Optimization Algorithm and the Energy Valley Optimizer. A rigorous k-fold cross-validation strategy confirms the robustness and generalization capability of the model. Experimental results demonstrate that the optimized hybrid framework surpasses individual classifiers, delivering high accuracy, strong scalability, and interpretability. This work contributes to proactive cybersecurity defenses by offering a reliable, data-driven, and explainable solution for real-time malicious website detection.
<i>In situ</i> X-ray Synchrotron Studies Reveal the Nucleation and Topotactic Transformation of Iron Sulfide Nanosheets
Asymmetric Synthesis of Diverse P(V) Compounds Bearing a C–P Bond via Desymmetrization of Phosphonic Dichlorides Catalyzed by a Chiral Bicyclic Imidazole
Prognostic value of ultrasonography findings in patients with cervical cancer
Precision-Engineered Crystalline Covalent Organic Framework Membranes with Staggered ABC Stacking for High-Performance Desalination
An experimental investigation of the drift ratio and its influencing factors in mechanical draft wet cooling towers
Machine Learning-Assisted Crystal Structure Prediction of Solid-State Electrolytes Reveals Superior Ionic Conductivity in Metastable Edge-Sharing Phases
Systematic review of healthcare-led and lay-led interventions for type 2 diabetes in community settings
Bioactive Artificial Cells as Autonomous Metabolic Actuators Enable Bidirectional Communication with Tumor Cells
Mechanistic insights into DEHP-induced progression of non-small cell lung cancer based on network toxicology and molecular docking
Short-Circuiting the SAM-Cycle in <i>Escherichia coli</i>
Promoting Formation and Suppressing Decomposition of H <sub>2</sub> O <sub>2</sub> via Photocarrier Flow at Au@TiO <sub>2</sub> Interfaces
A lightweight scalable and dynamic blockchain-based model for storing and retrieving patient healthcare records
Correction to “Phototheranostic Metal-Phenolic Networks with Antiexosomal PD-L1 Enhanced Ferroptosis for Synergistic Immunotherapy”
Saturation and texture geometry effects on plastron longevity on superhydrophobic surfaces
In Situ Exsolution of High-Density Ni Nanoparticles in LaAl <sub>0.3</sub> Mn <sub>0.2</sub> Ni <sub>0.5</sub> O <sub>3−δ</sub> Cathode for the Electro-Thermocatalytic CO <sub>2</sub> -Intensified Dry Reforming of Methane
The development of visual acuity and crowding reveals the slow fine-tuning of foveal vision
Abstract The adult visual system is characterised by high-resolution foveal vision and a peripheral field limited by crowding, the disruption to object recognition in clutter that gives a summary ‘gist’ over fine detail. In children, crowding is elevated foveally, with the estimated age where foveal crowding drops to adult-like levels varying widely from 5 to 12+ years. As crowding restricts key processes like reading, characterisation of this developmental trajectory is critical. Using methods optimised to measure crowding in children, adults and typically-developing children ( n = 119; 3–13 years) judged the orientation of a foveal ‘VacMan’ target either in isolation or surrounded by ‘ghost’ flankers. For isolated elements, acuity (measured as gap-size thresholds) dropped rapidly to adult-like levels at 5–6 years. Thresholds rose when flanked/crowded, with elevations highest at 3–4 years, persisting at 5–6 years, and dropping to adult-like levels at 7–8 years. A meta-analysis of our results and 13 prior studies reveals a consistent developmental trajectory, despite wide methodological variations. We further demonstrate that developmental crowding shows the same selectivity for target-flanker similarity as peripheral crowding, consistent with common mechanisms. This prolonged development reveals a shifting balance in the visual system between the processing of fine detail vs. the ‘gist’ of the scene.