Towards Efficient Data-Centric Robust Machine Learning with Noise-based Augmentation

The data-centric machine learning aims to find effective ways to build appropriate datasets which can improve the performance of AI models. In this paper, we mainly focus on designing an efficient data-centric scheme to improve robustness for models towards unforeseen malicious inputs in the black-b...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-03
Main Authors: Liu, Xiaogeng, Wang, Haoyu, Zhang, Yechao, Wu, Fangzhou, Hu, Shengshan
Format: Article
Language:English
Subjects:
Algorithms
Data augmentation
Machine learning
Noise
Perturbation
Random noise
Robustness (mathematics)
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The data-centric machine learning aims to find effective ways to build appropriate datasets which can improve the performance of AI models. In this paper, we mainly focus on designing an efficient data-centric scheme to improve robustness for models towards unforeseen malicious inputs in the black-box test settings. Specifically, we introduce a noised-based data augmentation method which is composed of Gaussian Noise, Salt-and-Pepper noise, and the PGD adversarial perturbations. The proposed method is built on lightweight algorithms and proved highly effective based on comprehensive evaluations, showing good efficiency on computation cost and robustness enhancement. In addition, we share our insights about the data-centric robust machine learning gained from our experiments.
ISSN:2331-8422