RNNSecureNet: Recurrent neural networks for Cyber security use-cases

TL;DR

This paper explores the application of recurrent neural networks (RNNs) in cybersecurity tasks such as incident detection, fraud detection, and malware classification, demonstrating superior performance over classical algorithms.

Contribution

It systematically evaluates different RNN architectures and parameters to identify the most effective configurations for cybersecurity use cases.

Findings

RNNs outperform classical machine learning algorithms in cybersecurity tasks.

Optimal RNN architectures depend on specific use cases and parameters.

RNNs effectively extract features and characteristics from complex cybersecurity data.

Abstract

Recurrent neural network (RNN) is an effective neural network in solving very complex supervised and unsupervised tasks. There has been a significant improvement in RNN field such as natural language processing, speech processing, computer vision and other multiple domains. This paper deals with RNN application on different use cases like Incident Detection, Fraud Detection, and Android Malware Classification. The best performing neural network architecture is chosen by conducting different chain of experiments for different network parameters and structures. The network is run up to 1000 epochs with learning rate set in the range of 0.01 to 0.5.Obviously, RNN performed very well when compared to classical machine learning algorithms. This is mainly possible because RNNs implicitly extracts the underlying features and also identifies the characteristics of the data. This helps to achieve better accuracy.