Izhikevich-Inspired Temporal Dynamics for Enhancing Privacy, Efficiency, and Transferability in Spiking Neural Networks

TL;DR

This paper introduces biologically inspired temporal spike transformations for spiking neural networks, improving privacy, efficiency, and transferability by modulating spike timing dynamics while maintaining competitive accuracy.

Contribution

It proposes two novel probabilistic temporal spike transformations, Poisson-Burst and Delayed-Burst, that enhance privacy and generalization in scalable SNN training.

Findings

Poisson-Burst achieves competitive accuracy with lower resource overhead.

Delayed-Burst offers stronger privacy protection with a modest accuracy trade-off.

Transformations improve privacy robustness and biological plausibility.

Abstract

Biological neurons exhibit diverse temporal spike patterns, which are believed to support efficient, robust, and adaptive neural information processing. While models such as Izhikevich can replicate a wide range of these firing dynamics, their complexity poses challenges for directly integrating them into scalable spiking neural networks (SNN) training pipelines. In this work, we propose two probabilistically driven, input-level temporal spike transformations: Poisson-Burst and Delayed-Burst that introduce biologically inspired temporal variability directly into standard Leaky Integrate-and-Fire (LIF) neurons. This enables scalable training and systematic evaluation of how spike timing dynamics affect privacy, generalization, and learning performance. Poisson-Burst modulates burst occurrence based on input intensity, while Delayed-Burst encodes input strength through burst onset timing. Through extensive experiments across multiple benchmarks, we demonstrate that Poisson-Burst maintains competitive accuracy and lower resource overhead while exhibiting enhanced privacy robustness against membership inference attacks, whereas Delayed-Burst provides stronger privacy protection at a modest accuracy trade-off. These findings highlight the potential of biologically grounded temporal spike dynamics in improving the privacy, generalization and biological plausibility of neuromorphic learning systems.