Model Capacity Vulnerability in Hyper-Parameters Estimation

Model Capacity Vulnerability in Hyper-Parameters Estimation

Machine learning models are vulnerable to a variety of data perturbation. Recent research mainly focuses on the vulnerability of model training and proposes various model-oriented defense methods to achieve robust machine learning. However, most of the existing research overlooks the vulnerability o...

Full description

Bibliographic Details
Main Authors: Wentao Zhao, Xiao Liu, Qiang Liu, Jiuren Chen, Pan Li
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Adversarial vulnerability
model capacity
hyper-parameter poisoning
gradient-based optimization
Online Access:https://ieeexplore.ieee.org/document/8968431/

Similar Items

Similar Items