Damage Resistance of an fMRI-Spiking Neural Network Based on Speech Recognition Against Stochastic Attack

Brain-like models are commonly used for pattern recognition, but they face significant performance degradation in neuromorphic hardware when exposed to complex electromagnetic environments. The human brain has adaptability to the exterior attack, and we expect that incorporating bio-plausibility int...

Full description

Saved in:
Bibliographic Details
Main Authors: Lei Guo, Huan Liu, Yihua Song, Nancheng Ma
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Biomimetics
Subjects:
Online Access:https://www.mdpi.com/2313-7673/10/7/415
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246396284141568
author Lei Guo
Huan Liu
Yihua Song
Nancheng Ma
author_facet Lei Guo
Huan Liu
Yihua Song
Nancheng Ma
author_sort Lei Guo
collection DOAJ
description Brain-like models are commonly used for pattern recognition, but they face significant performance degradation in neuromorphic hardware when exposed to complex electromagnetic environments. The human brain has adaptability to the exterior attack, and we expect that incorporating bio-plausibility into a brain-like model will enhance its robustness. However, brain-like models currently lack bio-plausibility. Therefore, we construct a spiking neural network (SNN) whose topology is constrained by human brain functional Magnetic Resonance Imaging (fMRI), called fMRI-SNN. To certify its damage resistance, we investigate speech recognition accuracy against stochastic attack. To reveal its damage-resistant mechanism, we explore the neural electrical features, adaptive modulation of synaptic plasticity, and topological features against stochastic attack. Research shows that fMRI-SNN surpasses SNNs with distinct topologies in recognition accuracy against stochastic attack, notably maintaining similar accuracy levels before and after stochastic attacks when the damage proportion is below 30%, demonstrating that our method improves the damage resistance of brain-like models. In addition, the change in neural electrical activity serves as interior manifestation, corresponding to the damage resistance of SNNs for recognition tasks, while the synaptic plasticity serves as the inherent determinant of the damage resistance, and the topology serves as a determinant impacting the damage resistance.
format Article
id doaj-art-74061bfcfba24bab832b7cc3411bd3fa
institution Kabale University
issn 2313-7673
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Biomimetics
spelling doaj-art-74061bfcfba24bab832b7cc3411bd3fa2025-08-20T03:58:30ZengMDPI AGBiomimetics2313-76732025-06-0110741510.3390/biomimetics10070415Damage Resistance of an fMRI-Spiking Neural Network Based on Speech Recognition Against Stochastic AttackLei Guo0Huan Liu1Yihua Song2Nancheng Ma3Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin 300131, ChinaTianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin 300131, ChinaTianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin 300131, ChinaTianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin 300131, ChinaBrain-like models are commonly used for pattern recognition, but they face significant performance degradation in neuromorphic hardware when exposed to complex electromagnetic environments. The human brain has adaptability to the exterior attack, and we expect that incorporating bio-plausibility into a brain-like model will enhance its robustness. However, brain-like models currently lack bio-plausibility. Therefore, we construct a spiking neural network (SNN) whose topology is constrained by human brain functional Magnetic Resonance Imaging (fMRI), called fMRI-SNN. To certify its damage resistance, we investigate speech recognition accuracy against stochastic attack. To reveal its damage-resistant mechanism, we explore the neural electrical features, adaptive modulation of synaptic plasticity, and topological features against stochastic attack. Research shows that fMRI-SNN surpasses SNNs with distinct topologies in recognition accuracy against stochastic attack, notably maintaining similar accuracy levels before and after stochastic attacks when the damage proportion is below 30%, demonstrating that our method improves the damage resistance of brain-like models. In addition, the change in neural electrical activity serves as interior manifestation, corresponding to the damage resistance of SNNs for recognition tasks, while the synaptic plasticity serves as the inherent determinant of the damage resistance, and the topology serves as a determinant impacting the damage resistance.https://www.mdpi.com/2313-7673/10/7/415spiking neural networkfunctional magnetic resonance imagingdamage resistancespeech recognition
spellingShingle Lei Guo
Huan Liu
Yihua Song
Nancheng Ma
Damage Resistance of an fMRI-Spiking Neural Network Based on Speech Recognition Against Stochastic Attack
Biomimetics
spiking neural network
functional magnetic resonance imaging
damage resistance
speech recognition
title Damage Resistance of an fMRI-Spiking Neural Network Based on Speech Recognition Against Stochastic Attack
title_full Damage Resistance of an fMRI-Spiking Neural Network Based on Speech Recognition Against Stochastic Attack
title_fullStr Damage Resistance of an fMRI-Spiking Neural Network Based on Speech Recognition Against Stochastic Attack
title_full_unstemmed Damage Resistance of an fMRI-Spiking Neural Network Based on Speech Recognition Against Stochastic Attack
title_short Damage Resistance of an fMRI-Spiking Neural Network Based on Speech Recognition Against Stochastic Attack
title_sort damage resistance of an fmri spiking neural network based on speech recognition against stochastic attack
topic spiking neural network
functional magnetic resonance imaging
damage resistance
speech recognition
url https://www.mdpi.com/2313-7673/10/7/415
work_keys_str_mv AT leiguo damageresistanceofanfmrispikingneuralnetworkbasedonspeechrecognitionagainststochasticattack
AT huanliu damageresistanceofanfmrispikingneuralnetworkbasedonspeechrecognitionagainststochasticattack
AT yihuasong damageresistanceofanfmrispikingneuralnetworkbasedonspeechrecognitionagainststochasticattack
AT nanchengma damageresistanceofanfmrispikingneuralnetworkbasedonspeechrecognitionagainststochasticattack