Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient
作者：互联网
郑重声明：原文参见标题，如有侵权，请联系作者，将会撤销发布！
arXiv:2001.01587v1 [cs.NE] 1 Jan 2020
Abstract
Keywords:
I. INTRODUCTION
II. PRELIMINARIES
A. Spiking Neural Networks
B. Gradient-based Adversarial Attack
FGSM.
BIM.
III. CHALLENGES IN SNN ATTACK
A. Challenges and Solutions
Acquiring Spatio-temporal Gradients.
Incompatible Format between Gradients and Inputs.
Gradient Vanishing Problem.
B. Comparison with Prior Work on SNN Attack
Trial-and-Error Input Perturbation.
SNN/ANN Model Conversion.
IV. ADVERSARIAL ATTACKS AGAINST SNNS
Input Data Format.
A. Attack Flow Overview
Spiking Inputs.
Image Inputs.
B. Acquisition of Spatio-Temporal Gradients
C. Gradient-to-Spike (G2S) Converter
Probabilistic Sampling.
Sign Extraction.
Overflow-aware Transformation.
D. Gradient Trigger (GT)
Element Selection.
Gradient Construction.
E. Overall Attack Algorithm
V. LOSS FUNCTION AND FIRING THRESHOLD
A. MSE and CE Loss Functions
B. Firing Threshold of the Penultimate Layer
VI. EXPERIMENT RESULTS
A. Experiment Setup
B. Influence of G2S Converter
C. Influence of GT
D. Influence of Loss Function and Firing Threshold
E. Effectiveness Comparison with Existing SNN Attack
F. Effectiveness Comparison with ANN Attack
VII. CONCLUSION AND DISCUSSION
标签：Exploring,Inputs,Gradient,Neural,Influence,SNN,Attack,Spiking 来源： https://www.cnblogs.com/lucifer1997/p/13062441.html