A Lightweight Approach for Network Intrusion Detection based on Self-Knowledge Distillation

TL;DR

This paper introduces LNet-SKD, a lightweight network for intrusion detection that balances high accuracy with low computational costs using self-knowledge distillation and a novel DeepMax block.

Contribution

The paper presents a novel lightweight intrusion detection model, LNet-SKD, utilizing DeepMax blocks and batch-wise self-knowledge distillation to enhance efficiency and accuracy.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Uses fewer parameters and less computation.

Maintains high detection accuracy with lightweight design.

Abstract

Network Intrusion Detection (NID) works as a kernel technology for the security network environment, obtaining extensive research and application. Despite enormous efforts by researchers, NID still faces challenges in deploying on resource-constrained devices. To improve detection accuracy while reducing computational costs and model storage simultaneously, we propose a lightweight intrusion detection approach based on self-knowledge distillation, namely LNet-SKD, which achieves the trade-off between accuracy and efficiency. Specifically, we carefully design the DeepMax block to extract compact representation efficiently and construct the LNet by stacking DeepMax blocks. Furthermore, considering compensating for performance degradation caused by the lightweight network, we adopt batch-wise self-knowledge distillation to provide the regularization of training consistency. Experiments on benchmark datasets demonstrate the effectiveness of our proposed LNet-SKD, which outperforms existing state-of-the-art techniques with fewer parameters and lower computation loads.