Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the Edge

TL;DR

This paper evaluates various neural network pruning methods to identify the most effective approach for resource-efficient intrusion detection on edge devices, revealing limited generalization of many methods to new cybersecurity datasets.

Contribution

It provides a comparative analysis of pruning algorithms' ability to generalize to cybersecurity tasks on simpler networks, highlighting the most suitable pruning method for edge intrusion detection.

Findings

Many pruning methods do not generalize well to new cybersecurity data.

Only a few algorithms perform acceptably across different pruning degrees.

The study identifies the most effective pruning method for resource-aware embedded intrusion detection.

Abstract

Artificial neural network pruning is a method in which artificial neural network sizes can be reduced while attempting to preserve the predicting capabilities of the network. This is done to make the model smaller or faster during inference time. In this work we analyze the ability of a selection of artificial neural network pruning methods to generalize to a new cybersecurity dataset utilizing a simpler network type than was designed for. We analyze each method using a variety of pruning degrees to best understand how each algorithm responds to the new environment. This has allowed us to determine the most well fit pruning method of those we searched for the task. Unexpectedly, we have found that many of them do not generalize to the problem well, leaving only a few algorithms working to an acceptable degree.