4 June 2025 in Journal of Future Artificial Intelligence and Technologies
AJAghoghovia Agajere Joseph-Brown
Aghoghovia Agajere Joseph-Brown
+1
Distributed Denial of Service (DDoS) attacks remain a critical threat to network infrastructure, necessitating timely and precise detection techniques to mitigate their impact. This study presents a hybrid deep learning framework that integrates the Three Conditions for Feature Aggregation (3ConFA) framework with a one-dimensional Convolutional Neural Network (1D-CNN) for effective DDoS detection. Initially, salient features were selected using the 3ConFA approach, which combines multi-filter feature ranking—based on Chi-square, Information Gain, and Decision Tree Recursive Feature Elimination (DT-RFE) to extract robust and relevant features from raw network traffic data. The training samples were balanced using the Adaptive Synthetic Sampling Approach (ADASYN) to address the high-class imbalance typically present in DDoS datasets. The refined features were then passed through a 1D-CNN model designed to learn temporal and spatial attack behavior patterns. Feature fusion was applied by concatenating the aggregated statistical features and the deep features learned by the CNN, then re-selected the most informative features using Recursive Feature Elimination with Cross-Validation (RFECV). The final classification was performed using a Softmax output layer, and the model was evaluated using 5-fold cross-validation and a separate test set. Experimental results demonstrated an average training accuracy of 99.42%, an F1-score of 99.35%, and an AUC-ROC of 99.87%. On the test set, the model achieved a detection accuracy of 99.56%, a precision of 99.61%, and an F1-score of 99.50%, with an AUC-ROC of 0.9982. The proposed hybrid approach outperforms traditional models such as Random Forest, Decision Tree, XGBoost, and standalone CNN, validating the synergistic impact of integrating 3ConFA with deep temporal convolutional modeling for accurate and interpretable DDoS attack detection.
8 May 2025 in Asian Journal of Research in Computer Science
High-dimensional datasets pose significant challenges in machine learning, including overfitting, increased computational complexity, and reduced model interpretability. In response to these challenges, this paper introduces the Three Conditions for Feature Aggregation (3ConFA) framework, a feature selection approach based on ensembles that seeks to reduce dimensionality without reducing predictive performance. The 3ConFA framework integrates three key techniques; Chi-square (χ²) test, Information Gain (IG), and Decision Tree-based Recursive Feature Elimination (DT-RFE), and applies stringent conditions to select only the most relevant features. A feature is retained if and only if it satisfies all three conditions: (1) IG score ≥ mean IG threshold, (2) χ² score ≥ mean χ² threshold, and (3) DT-RFE importance score = 1. Experimental evaluation on ten benchmark datasets demonstrates the effectiveness of the framework, achieving feature reductions of up to 98.75% (e.g., Dexter dataset) while improving classification accuracy (e.g., Madelon: 78% → 85%). Performance metrics (precision, recall, F1-score) were consistently enhanced after feature selection, confirming that 3ConFA enhances model generalization without tradeoff in critical information. The framework’s adaptability across diverse datasets highlights its potential for applications in fraud detection, healthcare, and image classification. This study contributes a structured, condition-driven feature aggregation approach that outperforms traditional filter and wrapper methods. Future work may explore adaptive thresholding and integration with deep learning models.
1 October 2025 in Indonesian Journal of Electrical Engineering and Computer Science
The flexibility of the unstructured supplementary service data (USSD) across mobile phones has caused its adoption surge as a payment channel. Its usage accommodates financial inclusivity and extends customer reach irrespective of their specific phone capabilities. With data conveyed on the USSD channel in plaintext–this has raised vulnerability issues with shoulder surfing attacks. The use of password yielded extra layer of security as authentication to USSD-based services. But, the rise in password guess attacks has necessitated a new scheme. This study is a randomized-obfuscated single factor authentication (SFA) mode via a 5-digit PIN-entry as requisite for the USSD channel. It yields a list via which users select a key-array that corresponds to their PIN as concealed in a 10-digit array. Expert assess of MoBiSafe’s usability and security against shoulder-surf yielded 10.1 msecs and 2.26 msecs respectively to outperform existing models that utilize direct/indirect PIN-entry as in USSD transactions. And this was found to be both secure, usable and acceptable.