Learning to Detect: An Enhanced DNN Model with Adaptive Attention for Classifying DDoS Traffic
Journal Title: Engineering and Technology Journal - Year 2025, Vol 10, Issue 06
Abstract
This research proposes an enhanced Deep Neural Network (DNN) model for detecting Distributed Denial of Service (DDoS) attacks using the CIC-IDS2017 dataset. The model incorporates a Adaptive Attention Layer (AAL) and data normalization to improve feature relevance and classification accuracy. Experiments were conducted across three feature sets (78, 39, and 25), multiple dataset sizes (4K, 40K, 225K), and a range of classification thresholds (0.1 to 1.0). Results demonstrate that optimal accuracy is consistently achieved at thresholds between 0.2 and 0.4. The study confirms a positive correlation between increased feature and dataset sizes and improved detection accuracy—especially when combined with AAL and normalization. The adaptive layer significantly enhances model performance by focusing on the most informative features and reducing both false positives and false negatives. The proposed model achieved a maximum accuracy of 99.93%, outperforming several benchmark methods. These findings underscore the value of attention-based deep learning approaches in developing robust, scalable, and real-time intrusion detection systems for cybersecurity applications.
Authors and Affiliations
Ahmed Saleh Khaled AL-Hurdi ,Mohammed Fadhl Abdullah,
Keywords
Related Articles
- EP ID EP768698
- DOI 10.47191/etj/v10i06.14
- Views 8
- Downloads 0
The Extraction of Alcea Rosea Organic Dye and Its Characterization of Optical Properties
In the present study, the optical properties of a natural dye extracted from Alcea rosea flowers were investigated. The color extraction procedure was performed using a nontoxic solvent ethanol to enhance human safety an...
DEVELOPING REGRESSION BASED APPROXIMATE QUANTITIES MODELS FOR QUANTIFICATION OF ELECTRICAL CABLES FOR RESIDENTIAL BUILDING CONSTRUCTION IN NIGERIA
In quantity surveying practice, the building and engineering standard method of measurement 4th edition stipulates that electrical final circuits should be enumerated during quantity take-off of electrical cables. This a...
The Interrelation Between Food, Water and Energy in the Island of Crete, Greece
Water, energy and food are important resources for human well-being while their demand is expected to increase in the future. These resources are interrelated and interdependent while they are threatened from climate cri...
DETERMINATION OF CR (III) AND CR (VI) IN WATER BY SELECTIVE SEPARATION AND PRECONCENTRATION ON HYBRID RESIN
Simple and rapid method has been developed for separation, preconcentration and determination of Cr(III) and Cr(VI) species in water by using selective hybrid R-Cu-(OH)2 resin (HCR). The effect of pH value on the adsorbe...
Leveraging Big Data Analytics for Risk Assessment and Regulatory Compliance Optimization in Business Operations
In the modern business environment, the increasing complexity of regulatory landscapes and the exponential growth of data have compelled organizations to explore innovative solutions for risk management and compliance op...