Smoothing inputs with a low-pass filter and comparing the classifier's confidence before and after smoothing detects FGSM and PGD adversarial examples on MNIST and ImageNet.
In: Joint European conference on machine learning and knowledge discovery in databases
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Automated Detection System for Adversarial Examples with High-Frequency Noises Sieve
Smoothing inputs with a low-pass filter and comparing the classifier's confidence before and after smoothing detects FGSM and PGD adversarial examples on MNIST and ImageNet.