Neuromorphic Graph Anomaly Detection via Adaptive STDP and Spiking Graph Neural Networks

TL;DR

This paper presents ASTDP-GAD, a neuromorphic graph anomaly detection framework combining spiking neural networks, STDP learning, and multi-scale temporal analysis for efficient and accurate detection in dynamic networks.

Contribution

It introduces a novel adaptive STDP-based spiking graph neural network architecture with theoretical guarantees and superior experimental performance.

Findings

Achieves up to 5x variance reduction in anomaly scores.

Demonstrates superior detection accuracy on nine datasets.

Provides theoretical guarantees for spike encoding and learning convergence.

Abstract

Anomaly detection in dynamic networks is critical for applications from cybersecurity to industrial monitoring, yet existing methods face challenges in energy efficiency, temporal precision, and adaptability. This paper introduces ASTDP-GAD, a novel Adaptive Spiking Temporal Dynamics Plasticity framework for Graph Anomaly Detection that integrates spiking graph neural networks with STDP learning for energy-efficient neuromorphic detection in dynamic networks. Our framework unifies spiking neural computation, STDP learning, and graph-based anomaly detection through the following key innovations: temporal spike graph encoding with adaptive Leaky Integrate-and-Fire (LIF) dynamics; LIF-based graph attention with lateral inhibition; event-driven hypergraph memory with STDP-inspired prototype updates; spike rate contrast pooling based on spiking irregularity; adaptive STDP layers capturing causal temporal relationships; and multi-scale temporal convolution with multi-factor anomaly fusion. Theoretical analysis provides rigorous guarantees: spike encoding preserves input information with resolution scaling linearly in simulation steps and hidden dimension; LIFGAT approximates any continuous attention function; hypergraph memory converges to optimal prototypes; contrast pooling achieves provable anomaly selection bounds; STDP learning converges stably; and multi-factor fusion produces calibrated scores with up to $5\times$ variance reduction. Extensive experiments on nine datasets on both dynamic and static graphs demonstrate superior anomaly detection accuracy while maintaining biological plausibility and energy efficiency for neuromorphic deployment.