A Radial Basis Function Neural Network-based Detection Method for Collusive Interest Flooding Attacks in Named Data Networks

In Named Data Networks (NDNs), the Collusive Interest Flooding Attack (CIFA) is a new variant of the Interest Flooding Attack (IFA). Due to the low-rate intermittency of a CIFA, it is more stealthy and deceptive than an IFA, posing challenges for most IFA detection schemes to effectively differentiate between normal and anomalous traffic. The use of machine learning algorithms to identify the characteristics of network traffic makes it possible to more accurately distinguish between normal network behavior and attacks. Based on this, to better detect CIFAs, we propose a Radial Basis Function (RBF) neural network-based scheme that can quickly detect CIFAs by identifying network traffic features and classifying them using an RBF neural network algorithm. The results show that the method has better detection performance than classical detection methods.