Recent Papers

Modern networks and services are vulnerable to Distributed Denial of Service (DDoS) assaults, which is why sophisticated detection methods are required. Improved Deep Convolutional Neural Networks (DCNNs) are the basis of our proposed method for DDoS attack detection in this research. The main goal is to create a strong and effective system that can detect and stop DDoS assaults in the blink of an eye. The suggested approach takes use of recent developments in deep learning to boost detection accuracy while decreasing false positives by improving the design of deep convolutional neural networks (DCNNs). Our new optimization algorithms and unique features make it possible for the model to detect complex patterns of DDoS attacks and other abnormalities in traffic that might be harmful. We run comprehensive tests utilizing benchmark datasets that include various DDoS assault scenarios to assess the efficacy of our improved DCNN-based detection system. The findings show that as compared to conventional approaches, there are substantial gains in detection accuracy, sensitivity, and specificity. Furthermore, our method is well-suited for implementation in high-throughput network settings due to its minimal computing cost and resilience against changing attack techniques.

Copyright © 2024 K. R. Prabha. This is an open access article distributed under the Creative Commons Attribution License.