Autoencoder for Design of Mitigation Model for DDOS Attacks via M-DBNN

Distributed Denial of Service (DDoS) attacks pose the greatest threat to continued and efficient operation Internet. It can lead website downtime, lost time money, disconnection hosting issues, vulnerability. Conventional machine learning methodologies are being harmed by reduced recognition rates greater false-positive due emergence new threats. As a result, high-performance classifiers with low high prediction accuracy required for DDoS detection system. Here, deep belief neural network is preferred, upgraded modified (M-DBNN) accurately detect from network. Enable database change specific format range, which helps M-DBNN classifier easily predict class. An advanced Chimp Optimization Algorithm (ChOA) used minimize error find best weight classifier; this leads accurate DDOS attack classes effectively. The proposed method evaluated CAIDA “DDoS Attack 2007” dataset. 0.87%, outcome compared those other existing methods (DNN), support vector (SVM), artificial (ANN), (NN). demonstrates great error.