DDSA: A Defense Against Adversarial Attacks Using Deep Denoising Sparse Autoencoder

DDSA: A Defense Against Adversarial Attacks Using Deep Denoising Sparse Autoencoder

Given their outstanding performance, the Deep Neural Networks (DNNs) models have been deployed in many real-world applications. However, recent studies have demonstrated that they are vulnerable to small carefully crafted perturbations, <italic>i.e.</italic>, adversarial examples, which...

Full description

Bibliographic Details
Main Authors: Yassine Bakhti, Sid Ahmed Fezza, Wassim Hamidouche, Olivier Deforges
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Deep neural network
security
adversarial attacks
defense
sparse autoencoder
denoising
Online Access:https://ieeexplore.ieee.org/document/8890816/

Internet

https://ieeexplore.ieee.org/document/8890816/

Similar Items