NEAILGMay 7, 2025

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

arXiv:2505.04034v12 citationsh-index: 4ICONS
Originality Incremental advance
AI Analysis

This work addresses privacy and efficiency issues in neuromorphic learning systems, offering incremental improvements through biologically grounded temporal dynamics.

The authors tackled the challenge of integrating biologically inspired temporal spike dynamics into scalable spiking neural networks (SNNs) by proposing two input-level transformations, Poisson-Burst and Delayed-Burst, which enhanced privacy robustness against membership inference attacks while maintaining competitive accuracy and lower resource overhead.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes