Detection of DDoS Attacks using Fine-Tuned Multi-Layer Perceptron Models

This study addresses a major cybersecurity challenge by focusing on the detection of Distributed Denial of Service (DDoS) attacks. These attacks pose a major threat to online services by overwhelming targets with traffic from multiple sources. Traditional detection approaches often fail to adapt to changing attack patterns, necessitating advanced machine-learning techniques. This study proposes a fine-tuned Multi-Layer Perceptron (MLP) model to improve DDoS detection accuracy while reducing false positives. This study uses fine-tuning techniques, such as hyperparameter optimization and transfer learning, to build a robust and adaptive detection framework. After extensive experiments with multiple data splits and cross-validation, the fine-tuned MLP model exhibited strong performance metrics with an average accuracy of 98.5%, precision of 98.1%, recall of 97.8%, and F1 score of 97.9%. These findings demonstrate the model's ability to successfully distinguish between benign and malicious traffic, enhancing network security and resilience. By overcoming the limitations of existing detection methods, this study adds new insights to the field of cybersecurity, providing a more precise and efficient approach to DDoS detection.