Comparison

The Artificial Neural Networks (ANN) have self-learning, selforganization, better fault tolerance and robustness, parallelism as of its advantages, so it got the attention of many researchers. ANN is used by many fellow researchers in detection of DDoS attacks as it can identify not only existing attack patterns but also unknown attack patterns. These techniques improve the intelligence and adaptability of intrusion detection systems (IDS). Self Organizing Maps (SOM), exact-STORM, Back Propagation Neural Network (BPNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short Term Memory (LSTM) are some efficient algorithms used by many researchers to detect DDoS attacks in networks based on software-defined networking. This is a comparison of the state-of-the-art DDoS defence solutions in SDN using ANNs.