Error-correcting output codes with ensemble diversity for robust learning in neural networks
Though deep learning has been applied successfully in many scenarios, malicious inputs with human-imperceptible perturbations can make it vulnerable in real applications. This paper proposes an error-correcting neural network (ECNN) that combines a set of binary classifiers to combat adversarial exam...
Main Authors: | Song, Yang, Kang, Qiyu, Tay, Wee Peng |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Conference Paper |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/147336 |
Similar Items
-
On the robustness of graph neural diffusion to topology perturbations
by: Song, Yang, et al.
Published: (2023) -
RobustLoc: robust camera pose regression in challenging driving environments
by: Wang, Sijie, et al.
Published: (2023) -
Robust wideband speech coding
by: Wang, Hongqiang
Published: (2008) -
Stable neural ODE with Lyapunov-stable equilibrium points for defending against adversarial attacks
by: Kang, Qiyu, et al.
Published: (2023) -
Training-free neural active learning with initialization robustness guarantees
by: Singh, Jasraj
Published: (2023)