Identifikasi Serangan Low-Rate DDOS Berbasis Deep Learning

LowRate DDoS (LDDoS) is a variation of attack that sends fewer packets than conventional attacks. However, by sending smaller number and using unique period, low-rate very effective in reducing the quality an internet network-based service due to full access. On other hand, with its nature also makes it difficult detect because looks more mixed normal user The Deep Learning model will be used this research RNN LSTM (Long Short Term Memory) model. neural network architecture which good enough process sequential data. This better simple method adapted SKKNI No. 299 2020. carried out until development stage, namely evaluation From results has been done, can concluded classify DDOS attacks feature selection. accuracy training data on validation around 98% after visualizing for loss, quite good, aka there no underfitting or overfitting. While obtained testing 0.97%.