EagerNet: Early Predictions of Neural Networks for Computationally Efficient Intrusion Detection

TL;DR

EagerNet is a neural network architecture designed for intrusion detection that makes early predictions to reduce computational resources while maintaining accuracy, suitable for real-time security applications.

Contribution

It introduces a novel early prediction architecture for neural networks that balances speed and accuracy in intrusion detection tasks.

Findings

Early predictions save energy and computation.

Comparable accuracy to full models with fewer evaluations.

Effective on multiple intrusion detection datasets.

Abstract

Fully Connected Neural Networks (FCNNs) have been the core of most state-of-the-art Machine Learning (ML) applications in recent years and also have been widely used for Intrusion Detection Systems (IDSs). Experimental results from the last years show that generally deeper neural networks with more layers perform better than shallow models. Nonetheless, with the growing number of layers, obtaining fast predictions with less resources has become a difficult task despite the use of special hardware such as GPUs. We propose a new architecture to detect network attacks with minimal resources. The architecture is able to deal with either binary or multiclass classification problems and trades prediction speed for the accuracy of the network. We evaluate our proposal with two different network intrusion detection datasets. Results suggest that it is possible to obtain comparable accuracies to simple FCNNs without evaluating all layers for the majority of samples, thus obtaining early predictions and saving energy and computational efforts.