Robust SNN

Robust Spiking Neural Networks (SNNs) research focuses on improving the resilience of these energy-efficient neural networks to various challenges, including adversarial attacks and noisy or incomplete data. Current efforts concentrate on developing adaptive training algorithms that dynamically adjust neuron thresholds and sparsity regularization techniques to enhance robustness, as well as exploring robust conversion methods from traditional Artificial Neural Networks (ANNs). This work is significant because it addresses critical limitations of SNNs for real-world deployment, paving the way for more reliable and secure applications in areas like neuromorphic computing and edge AI.

Papers

July 28, 2024

To Spike or Not to Spike, that is the Question
Sanaz Mahmoodi Takaghaj, Jack Sampson
Neuromorphic Datasets Spike Timing Dead Neuron Adaptive Threshold Spike Threshold Robust SNN

May 30, 2024

Enhancing Adversarial Robustness in SNNs with Sparse Gradients
Yujia Liu, Tong Bu, Jianhao Ding, Zecheng Hao, Tiejun Huang, Zhaofei Yu
Adversarial Attack Native Robustness Adversarial Robustness Adversarial Perturbation Spiking Neural Network Sparse Gradient Robust SNN

November 15, 2023

Adversarially Robust Spiking Neural Networks Through Conversion
Ozan Özdenizci, Robert Legenstein
Adversarial Robustness Spiking Neural Network Neuromorphic Computing Automated Conversion Robust SNN

October 25, 2023

Balancing Augmentation with Edge-Utility Filter for Signed GNNs
Ke-Jia Chen, Yaming Ji, Youran Qu, Chuhan Xu
Gene Level GNN Dynamic Balance GNN Backbone Marginal Feature Elastic Instability Robust SNN

September 20, 2022

Audit and Improve Robustness of Private Neural Networks on Encrypted Data
Jiaqi Xue, Lei Xu, Lin Chen, Weidong Shi, Kaidi Xu, Qian Lou
Neural Network Native Robustness Privacy Preserving Audit Evidence Robust SNN

June 30, 2022

Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN
Kuan Li, Yang Liu, Xiang Ao, Jianfeng Chi, Jinghua Feng, Hao Yang, Qing He
Graph Neural Network Graph Structure Edge Weight GCN Model Reliable Representation Robust SNN Adversarial Edge Structure Refinement

May 27, 2022

EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks
Runlin Lei, Zhen Wang, Yaliang Li, Bolin Ding, Zhewei Wei
Graph Neural Network Native Robustness Graph Machine Learning Spectral GNN Hop Neighbor Robust SNN Polynomial Graph Filter

April 12, 2022

Toward Robust Spiking Neural Network Against Adversarial Perturbation
Ling Liang, Kaidi Xu, Xing Hu, Lei Deng, Yuan Xie
Native Robustness Adversarial Perturbation Spiking Neural Network Neuron Model Robust Training Robust SNN