Dynamically Self-Adapting and Growing Intrusion Detection System
The ever-growing use of the Internet comes with a surging escalation of communication and data access. Most existing intrusion detection systems have assumed the one-size-fits-all solution model. Such IDS is not as economically sustainable for all organizations. Furthermore, studies have found that recurrent neural network out-performs feed-forward neural network, and Elman network. This paper, therefore, proposes a scalable application-based model for detecting attacks in a communication network using recurrent neural network architecture. Its suitability for online real-time applications and its ability to self-adjust to changes in its input environment cannot be over-emphasized.