Surrogate Models of Spiking Neural Networks for Explainability

Jane Jung, Matthew M. Y. Kuo, Nathan Allen

Abstract: This paper presents an Explainable AI (XAI) method for explaining Spiking Neural Networks (SNNs) through surrogate modeling. The proposed method involves translating trained SNNs into an equivalent Multi-Layer Perceptron (MLP) model, and enabling the use of standard post-hoc explanation techniques such as Shapley Additive Explanation (SHAP). The translation framework, implemented in Nengo, includes a custom weight-mapping and Leaky Integrate-and-Fire Rate (LIFRate)-based activation to approximate spiking behaviour. On a binary Distributed Denial-of-Service (DDoS) detection task, the translated model achieved lower accuracy (0.87) than benchmark MLPs (0.99–1.00), but identified the same key features. Further experiments showed that Recursive Least Squares (RLS)-trained SNNs consistently outperformed Prescribed Error-Sensitivity (PES)-trained variants.

External IDs:doi:10.1007/978-981-95-4575-9_3