Title: Predicting cyber attacks by deep learning
Authors: Maochao Xu - Illinois State University (United States) [presenting]
Abstract: It is important to understand to what extent, and in what perspectives, cyber attacks can be predicted. Being able to predict cyber attacks, even for minutes (if not hours) ahead-of-time, would allow the defender to proactively allocate resources for adequate defense (e.g., dynamically allocating sufficient resources for deep packet inspection or flow-level assembly and analysis). We show that how the deep learning can be used for modeling and predicting the cyber attacks. The real data analysis shows that the proposed deep learning algorithm has a very satisfactory prediction performance.