Paper Title
Integrated Ai Framework for Detection and Classification of BOTNET-Based DDOS Attacks

Abstract
Botnet-based Distributed Denial of Service (DDoS) attacks have emerged as a major cybersecurity threat in modern IoT and networked environments due to their large-scale and stealthy traffic behaviour. Traditional detection mechanisms are often ineffective in identifying evolving attack patterns and minimizing false alarms. To address this issue, this paper proposes an integrated artificial intelligence framework named RF-CNNbALO, which combines Random Forest (RF), Convolutional Neural Networks (CNN), and Ant Lion Optimizer (ALO) for effective detection and classification of botnet-driven DDoS attacks. The Random Forest model is employed for efficient feature selection and traffic classification, while CNN is utilized to learn complex traffic patterns associated with malicious behaviour. Furthermore, the Ant Lion Optimizer enhances model performance through optimal parameter tuning and feature optimization. The proposed framework was evaluated using the Bot-IoT dataset, and the experimental results demonstrated superior detection performance with an accuracy of 99.65%, precision of 99.55%, recall of 99.46%, and F1-score of 99.24%. The results confirm that the proposed RFCNNbALO framework provides reliable and efficient detection of botnet-based DDoS attacks in dynamic network environments. Keywords - Machine Learning, Deep Learning, DDoS Detection, Botnet Detection, Internet of Things, Ant Lion Optimizer, Cybersecurity