Assessing Optimizer Impact on DNN Model Sensitivity to Adversarial Examples

Assessing Optimizer Impact on DNN Model Sensitivity to Adversarial Examples

Deep Neural Networks (DNNs) have been gaining state-of-the-art achievement compared with many traditional Machine Learning (ML) models in diverse fields. However, adversarial examples challenge the further deployment and application of DNNs. Analysis has been carried out for studying the reasons of...

Full description

Bibliographic Details
Main Authors: Yixiang Wang, Jiqiang Liu, Jelena Misic, Vojislav B. Misic, Shaohua Lv, Xiaolin Chang
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Adversarial examples
deep neural network
machine learning
stochastic gradient descent optimization algorithm
transferability
Online Access:https://ieeexplore.ieee.org/document/8878095/

Internet

https://ieeexplore.ieee.org/document/8878095/

Similar Items