Forecasting Future DDoS Attacks using Long Short Term Memory (LSTM) Model

This paper forecasts future Distributed Denial-of-Service (DDoS) attacks using deep learning models.Although several studies address forecasting DDoS attacks, they remain relatively limited compared todetection-focused research. By studying the current trends and forecasting based on newer and updateddatasets, mitigation plans against the attacks can be planned and formulated. The methodology used in thisresearch work conforms to the Cross Industry Standard Process for Data Mining (CRISP-DM) model.Leveraging cyberattack data from the COVID-19 period (2019–2020), sourced from Digital Attack Mapand compiled by Arbor Networks, the study aims to identify recent attack trends and forecast future activityto support proactive mitigation strategies. The dataset was examined using statistical analysis techniquesto identify prevailing patterns, with emphasis on the frequency of attacks, the duration of attack instances,and the maximum throughput recorded during each incident. Compared to other deep learning models, theLSTM model is proposed for its ability to learn long-term temporal patterns in evolving DDoS traffic. Theperformance of LSTM model was evaluated using Mean Squared Error (MSE) under varying neuroncounts and window sizes. While the model demonstrated limited predictive accuracy in terms of absolutevalues, the visual comparison between the predicted and actual data using line charts revealed closealignment in trend patterns. This suggests that the model captures the underlying temporal dynamics of thedata, thereby providing a promising foundation for future model optimization and performanceenhancement.