An Efficient Method for Sample Adversarial Perturbations against Nonlinear Support Vector Machines.

Wen Su Qingna Li

Published in: CoRR (2022)

Keyphrases

computational cost
experimental evaluation
synthetic data
cross validation
support vector machine
significant improvement
high precision

support vector
neural network
computational complexity
similarity measure
clustering algorithm
high accuracy

segmentation method
training samples
high order
test data
decision function
detection method

computationally efficient
model selection
classification accuracy
preprocessing
decision trees
feature selection