CyberShield: A Hybrid CNN-GRU Model for Intelligent DDoS Attack Recognition
Shubrika Sharma, himanshu ., Dayal Chandra Sati, Pardeep Kumar, Monika · 2024
The ongoing threat of Distributed Denial of Service (DDoS) attacks presents an important challenge for online service providers, especially when it comes to E-Commerce platforms. This research focuses on creating a powerful identification system with deep learning methods to counter this threat. To be more precise, Gated Recurrent Units (GRU) and Convolutional Neural Networks (CNN) is used for separately examine and comprehend the patterns predictive of DDoS attacks. This hybrid model combines Gated Recurrent Units (GRU) and Convolutional Neural Networks (CNN) to tackle the problem of DDoS attacks in e-commerce. By utilizing the temporal and spatial dependencies present in DDoS attack data, this method improves accuracy and resilience. In this work, first the individual CNN and GRU models are trained and analyzed, then a hybrid model is created. By utilizing a meticulously selected dataset, the hybrid model is analyzed. The results demonstrate its potential as a cutting-edge and trustworthy method for identifying DDoS attacks in e-commerce settings.