Neuromorphic Cybersecurity with Semi-supervised Lifelong Learning

TL;DR

This paper introduces a neuromorphic, bio-inspired SNN architecture for lifelong network intrusion detection that learns incrementally, reduces forgetting, and is suitable for low-power neuromorphic hardware deployment.

Contribution

It proposes a novel SNN-based NIDS with structural plasticity and a new learning rule, enabling continual learning and robustness against catastrophic forgetting.

Findings

Achieved 85.3% accuracy on UNSW-NB15 benchmark.

Demonstrated high operational sparsity for low-power neuromorphic hardware.

Enabled incremental learning of new threats with preserved knowledge.

Abstract

Inspired by the brain's hierarchical processing and energy efficiency, this paper presents a Spiking Neural Network (SNN) architecture for lifelong Network Intrusion Detection System (NIDS). The proposed system first employs an efficient static SNN to identify potential intrusions, which then activates an adaptive dynamic SNN responsible for classifying the specific attack type. Mimicking biological adaptation, the dynamic classifier utilizes Grow When Required (GWR)-inspired structural plasticity and a novel Adaptive Spike-Timing-Dependent Plasticity (Ad-STDP) learning rule. These bio-plausible mechanisms enable the network to learn new threats incrementally while preserving existing knowledge. Tested on the UNSW-NB15 benchmark in a continual learning setting, the architecture demonstrates robust adaptation, reduced catastrophic forgetting, and achieves $85.3$\% overall accuracy. Furthermore, simulations using the Intel Lava framework confirm high operational sparsity, highlighting the potential for low-power deployment on neuromorphic hardware.